This is the multi-page printable view of this section. Click here to print.

Return to the regular view of this page.

Dapr MCP server

Expose Dapr building blocks to AI agents as Model Context Protocol tools

The Dapr MCP server (dapr/dapr-mcp-server) is a standalone Model Context Protocol (MCP) server, written in Go, that runs next to a Dapr sidecar. It turns the sidecar’s building blocks (state, pub/sub, bindings, secrets, service invocation, actors, distributed lock, cryptography, and conversation) into MCP tools that any MCP client can call: Claude Desktop, Cursor, Claude Code, VS Code, Dapr Agents, or your own agent.

How it differs from the rest of this section

The other pages in this section cover how the Dapr runtime connects agents to MCP servers you already have, either through service invocation or with the MCPServer resource. The Dapr MCP server works the other way round: it is an MCP server, and the tools it serves are Dapr APIs. It is a separate binary with its own release cycle, not a feature of daprd. The two fit together. You can run the Dapr MCP server as a Dapr app and reach it through the service invocation path, or declare it as an MCPServer resource like any other MCP server.

When to use it

Use the Dapr MCP server when you want an agent to:

  • Persist or read data through a Dapr state store, with transactions where the store supports them.
  • Publish events, call other Dapr apps or actors, or reach external systems through output bindings.
  • Coordinate with other workers using a distributed lock.
  • Read secrets, encrypt or decrypt data, or hand a prompt to another LLM through a conversation component.

The agent gets the same component abstraction your services use, so swapping Redis for PostgreSQL or Kafka for RabbitMQ needs no change to the agent.

You don’t need it for plain computation, one-off text generation, or local file and process access. Those don’t need a Dapr sidecar.

How it works

  1. The server starts and connects to the Dapr sidecar over gRPC, using the standard Dapr SDK settings (DAPR_GRPC_PORT, DAPR_GRPC_ENDPOINT). It retries the connection up to five times, then exits.
  2. It reads the sidecar’s metadata and registers tools for each building block that has at least one component loaded. Three tools are always registered: get_components, invoke_service, and invoke_actor_method.
  3. It serves MCP over stdio (the default, for local clients that launch the server themselves) or over streamable HTTP (with --http, for remote and shared deployments). Authentication, health endpoints, and CORS apply to the HTTP transport only.

Tools follow the components loaded in the sidecar, with no restart. When component hot reloading adds the first component of a type (for example the first pub/sub component), the server registers that type’s tools the next time a client lists tools or calls get_components, and notifies connected clients that the tool list changed. Removing the last component of a type removes its tools. Clients that read the tool list only once, as many agent frameworks do, need to reconnect to see the change.

Every tool carries MCP safety annotations (readOnlyHint, destructiveHint, idempotentHint) and a description that tells the model when to use it. The server’s instructions tell the model to call get_components first and never to invent component names, keys, or topics.

Security considerations

The server can do anything its Dapr sidecar can do, and it returns tool results, including secret values from get_secret and get_bulk_secrets, to the model. Limit what the sidecar can reach:

  • Load only the components the agent needs, and use component scopes and secret scopes to narrow access further.
  • Turn on authentication whenever you serve over HTTP to anything other than localhost.
  • Treat tools marked destructive (delete_state, execute_transaction, invoke_service, invoke_actor_method, invoke_output_binding, encrypt_data) as needing human confirmation in your MCP client.

Next steps

1 - Getting started with the Dapr MCP server

Install the Dapr MCP server, run it with a Dapr sidecar, and connect an MCP client over stdio or streamable HTTP

This guide installs the Dapr MCP server, runs it next to a Dapr sidecar with two in-memory components, and connects an MCP client to it.

Prerequisites

Step 1: Install the server

Pick one of the following.

Each GitHub release publishes a binary per platform, named dapr-mcp-server-<os>-<arch>, with a checksums.txt file. Builds are available for linux-amd64, linux-arm64, darwin-amd64, darwin-arm64, and windows-amd64 (with an .exe suffix).

Download the binary, check it against checksums.txt, and move it onto your PATH. On Arm, use linux-arm64.

curl -LO https://github.com/dapr/dapr-mcp-server/releases/latest/download/dapr-mcp-server-linux-amd64
curl -LO https://github.com/dapr/dapr-mcp-server/releases/latest/download/checksums.txt
sha256sum --ignore-missing -c checksums.txt
chmod +x dapr-mcp-server-linux-amd64
sudo mv dapr-mcp-server-linux-amd64 /usr/local/bin/dapr-mcp-server

Download the binary, check it against checksums.txt, and move it onto your PATH. On an Intel Mac, use darwin-amd64.

curl -LO https://github.com/dapr/dapr-mcp-server/releases/latest/download/dapr-mcp-server-darwin-arm64
curl -LO https://github.com/dapr/dapr-mcp-server/releases/latest/download/checksums.txt
shasum -a 256 --ignore-missing -c checksums.txt
chmod +x dapr-mcp-server-darwin-arm64
sudo mv dapr-mcp-server-darwin-arm64 /usr/local/bin/dapr-mcp-server

In PowerShell, download the binary to $Env:LOCALAPPDATA\dapr-mcp-server, check it against checksums.txt, and add the folder to your user PATH:

$base = "https://github.com/dapr/dapr-mcp-server/releases/latest/download"
$dir = "$Env:LOCALAPPDATA\dapr-mcp-server"
New-Item -ItemType Directory -Force -Path $dir | Out-Null
Invoke-WebRequest "$base/dapr-mcp-server-windows-amd64.exe" -OutFile "$dir\dapr-mcp-server.exe"
Invoke-WebRequest "$base/checksums.txt" -OutFile "$dir\checksums.txt"
$expected = ((Select-String -Path "$dir\checksums.txt" -Pattern "dapr-mcp-server-windows-amd64.exe").Line -split "\s+")[0]
$actual = (Get-FileHash "$dir\dapr-mcp-server.exe" -Algorithm SHA256).Hash.ToLower()
if ($actual -ne $expected) { throw "Checksum mismatch for dapr-mcp-server.exe" }
$userPath = [Environment]::GetEnvironmentVariable("Path", "User")
if (($userPath -split ";") -notcontains $dir) {
    [Environment]::SetEnvironmentVariable("Path", (($userPath, $dir) | Where-Object { $_ }) -join ";", "User")
}

Open a new terminal so the updated PATH takes effect.

</div>

Requires Go 1.26.6 or later.

go install github.com/dapr/dapr-mcp-server/cmd/dapr-mcp-server@latest

A binary built this way reports its version as dev, because the version is stamped in only by the release build.

Multi-arch images (linux/amd64, linux/arm64) are published to the GitHub Container Registry, tagged with the release version. Stable releases also update latest.

docker pull ghcr.io/dapr/dapr-mcp-server:latest

The image runs as a non-root user, listens on port 8080 with --http 0.0.0.0:8080 by default, and includes a HEALTHCHECK. See Run on Kubernetes for how to pair it with a sidecar.

Check the install:

dapr-mcp-server --version

Step 2: Define components

The server registers tools only for building blocks that have a component loaded. Create a components folder with an in-memory state store and pub/sub broker:

mkdir -p components

components/statestore.yaml:

apiVersion: dapr.io/v1alpha1
kind: Component
metadata:
  name: statestore
spec:
  type: state.in-memory
  version: v1

components/pubsub.yaml:

apiVersion: dapr.io/v1alpha1
kind: Component
metadata:
  name: pubsub
spec:
  type: pubsub.in-memory
  version: v1

With these two components the server registers the three core tools plus the state and pub/sub tools. Add components of other types (bindings.*, secretstores.*, lock.*, crypto.*, conversation.*) to expose their tools. See the tool reference for the full mapping.

Step 3: Run and connect

Over stdio (Claude Desktop, Cursor)

With stdio, the MCP client starts the server process itself. Run the sidecar on its own first, on a fixed gRPC port:

dapr run --app-id dapr-mcp-server --dapr-grpc-port 50001 --resources-path ./components

Leave it running, then point your client at the binary. Use the absolute path, because clients don’t always inherit your shell’s PATH. On Windows, that’s the full path to dapr-mcp-server.exe, with each backslash doubled in JSON (for example, C:\\Users\\<you>\\AppData\\Local\\dapr-mcp-server\\dapr-mcp-server.exe).

Edit claude_desktop_config.json (on macOS, ~/Library/Application Support/Claude/claude_desktop_config.json; on Windows, %APPDATA%\Claude\claude_desktop_config.json) and restart Claude Desktop:

{
  "mcpServers": {
    "dapr": {
      "command": "/usr/local/bin/dapr-mcp-server",
      "env": {
        "DAPR_GRPC_PORT": "50001"
      }
    }
  }
}

Add the server to ~/.cursor/mcp.json, or to .cursor/mcp.json in a project:

{
  "mcpServers": {
    "dapr": {
      "command": "/usr/local/bin/dapr-mcp-server",
      "env": {
        "DAPR_GRPC_PORT": "50001"
      }
    }
  }
}
claude mcp add dapr --env DAPR_GRPC_PORT=50001 -- /usr/local/bin/dapr-mcp-server

Ask the assistant to list your Dapr components. It calls get_components and reports statestore and pubsub. From there, try “save the key greeting with value hello to the state store” and “read it back”.

The server writes its logs as JSON to stderr, so they never mix with the MCP messages on stdout. Most clients show stderr in their MCP log view.

Over streamable HTTP

Pass --http with a listen address to serve MCP over streamable HTTP. Here dapr run starts both the sidecar and the server, and sets DAPR_GRPC_PORT for it:

dapr run --app-id dapr-mcp-server --resources-path ./components -- dapr-mcp-server --http localhost:8080

The MCP endpoint is http://localhost:8080/. Check that the server is up and can reach its sidecar:

curl http://localhost:8080/readyz
Invoke-RestMethod http://localhost:8080/readyz

A 200 response with "status":"healthy" means it’s ready. A 503 means the sidecar isn’t reachable; PowerShell reports it as an error.

Connect a client that supports streamable HTTP:

{
  "mcpServers": {
    "dapr": {
      "url": "http://localhost:8080/"
    }
  }
}
claude mcp add --transport http dapr http://localhost:8080/
import asyncio

from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client


async def main():
    async with streamablehttp_client("http://localhost:8080/") as (read, write, _):
        async with ClientSession(read, write) as session:
            await session.initialize()
            tools = await session.list_tools()
            print([tool.name for tool in tools.tools])
            result = await session.call_tool("get_components", {})
            print(result.structuredContent)


asyncio.run(main())

Run on Kubernetes

On Kubernetes, run the container image with the Dapr sidecar injected. The injector sets DAPR_GRPC_PORT in the server’s container, so no extra configuration is needed to find the sidecar. Point the probes at the server’s health endpoints:

apiVersion: apps/v1
kind: Deployment
metadata:
  name: dapr-mcp-server
spec:
  replicas: 1
  selector:
    matchLabels:
      app: dapr-mcp-server
  template:
    metadata:
      labels:
        app: dapr-mcp-server
      annotations:
        dapr.io/enabled: "true"
        dapr.io/app-id: "dapr-mcp-server"
    spec:
      containers:
        - name: dapr-mcp-server
          image: ghcr.io/dapr/dapr-mcp-server:latest
          ports:
            - containerPort: 8080
          startupProbe:
            httpGet:
              path: /startupz
              port: 8080
            failureThreshold: 30
            periodSeconds: 2
          livenessProbe:
            httpGet:
              path: /livez
              port: 8080
          readinessProbe:
            httpGet:
              path: /readyz
              port: 8080
---
apiVersion: v1
kind: Service
metadata:
  name: dapr-mcp-server
spec:
  selector:
    app: dapr-mcp-server
  ports:
    - port: 8080
      targetPort: 8080

Add authentication and telemetry settings as env entries on the container; see the configuration reference.

Streamable HTTP sessions are held in the server’s memory. If you run more than one replica, configure session affinity on whatever routes traffic to them, so that each client keeps reaching the same replica.

Next steps

2 - Dapr MCP server configuration reference

Every command-line flag and environment variable the Dapr MCP server reads, with defaults

The Dapr MCP server takes a few command-line flags and reads everything else from environment variables. The server checks authentication settings at startup and exits with an error if they are invalid or incomplete, rather than starting without protection.

Command-line flags

FlagDefaultDescription
--http <addr>Not set (stdio)Serve streamable HTTP on this address, for example localhost:8080 or 0.0.0.0:8080, instead of stdio. The health endpoints are served on the same address.
--versionfalsePrint the version and exit.
--health-checkfalseRequest /livez from a running server and exit with 0 on a 200 response, 1 otherwise. The container image uses this for its HEALTHCHECK.
--health-check-addr <host:port>From --http, else localhost:8080Address that --health-check probes. A wildcard host such as 0.0.0.0 is probed as localhost.

Server and Dapr connection

VariableDefaultDescription
DAPR_GRPC_PORT50001Port of the Dapr sidecar’s gRPC API on 127.0.0.1. dapr run and the Kubernetes sidecar injector set this for you.
DAPR_GRPC_ENDPOINTNot setFull address of the sidecar’s gRPC API. Takes precedence over DAPR_GRPC_PORT.
DAPR_API_TOKENNot setToken sent to the sidecar when it requires API token authentication.
DAPR_CLIENT_TIMEOUT_SECONDS5Timeout for each attempt to connect to the sidecar. The server makes up to five attempts, two seconds apart, then exits.
DAPR_MCP_SERVER_LOG_LEVELinfoLog level: debug, info, warn, or error. Logs are JSON on stderr. At debug, request headers are logged with credential headers redacted.

The DAPR_* connection variables are read by the Dapr Go SDK that the server uses.

HTTP transport

These settings apply only when the server runs with --http.

VariableDefaultDescription
DAPR_MCP_CORS_ORIGINNot setOrigin allowed to call the server from a browser, for example https://app.example.com. When set, the server adds CORS headers to every response and answers OPTIONS preflight requests. When not set, no CORS headers are sent and browsers on other origins are refused. Set it only for a browser-based MCP client on another origin.

The server always serves /livez, /readyz, and /startupz without authentication; see Health endpoints. MCP requests are served on every other path, so http://<host>:<port>/ is the MCP endpoint. The one exception is /dapr/subscribe, which returns an empty subscription list for the Dapr sidecar and also needs no authentication.

Authentication

Authentication applies to the HTTP transport. See Authentication for how the modes work and for examples.

VariableDefaultDescription
AUTH_MODENot set (disabled)oidc, spiffe, dapr-sentry, or hybrid turns authentication on. Not set, or disabled, turns it off.
OIDC_ENABLEDfalseIn hybrid mode, accept OIDC tokens. Ignored in other modes.
OIDC_ISSUER_URLNot setOIDC issuer URL. Required when OIDC is on.
OIDC_CLIENT_IDNot setExpected aud claim. Required when OIDC is on.
OIDC_ALLOWED_ALGORITHMSRS256,ES256Comma-separated signing algorithms to accept.
OIDC_SKIP_ISSUER_CHECKfalseSkip the iss check. For development only.
SPIFFE_ENABLEDfalseIn hybrid mode, accept SPIFFE JWT-SVIDs. Ignored in other modes.
SPIFFE_TRUST_DOMAINNot setTrust domain that callers must belong to. Required when SPIFFE is on.
SPIFFE_SERVER_IDNot setThis server’s SPIFFE ID, which callers’ JWT-SVIDs must use as their audience. Required when SPIFFE is on.
SPIFFE_ENDPOINT_SOCKETNot setAddress of the SPIFFE Workload API, for example unix:///run/spire/sockets/agent.sock.
SPIFFE_ALLOWED_CLIENTSNot set (any workload in the trust domain)Comma-separated SPIFFE IDs allowed to call the server.
DAPR_SENTRY_ENABLEDfalseIn hybrid mode, accept Dapr Sentry JWTs. Ignored in other modes.
DAPR_SENTRY_JWKS_URLNot setURL of the Sentry JWKS. Required when Dapr Sentry is on.
DAPR_SENTRY_TRUST_DOMAINNot setTrust domain of the SPIFFE ID in the token’s sub claim. Required when Dapr Sentry is on.
DAPR_SENTRY_AUDIENCENot setExpected aud claim. Required when Dapr Sentry is on.
DAPR_SENTRY_ISSUERNot setExpected iss claim. Checked only when set.
DAPR_SENTRY_TOKEN_HEADERAuthorizationHeader to read the token from. Despite its name, it applies in every auth mode, not only Dapr Sentry. A custom header carries the raw token, without a Bearer prefix.
DAPR_SENTRY_JWKS_REFRESH_INTERVAL5mHow often to refresh the JWKS, as a Go duration. Minimum 30s.

Telemetry

Telemetry is off until an OTLP endpoint is set. See Observability for what the server emits.

VariableDefaultDescription
OTEL_EXPORTER_OTLP_ENDPOINTNot setOTLP collector endpoint for all signals, for example http://otel-collector:4317. An endpoint without a scheme uses TLS.
OTEL_EXPORTER_OTLP_PROTOCOLgrpcgrpc or http/protobuf. http/json falls back to http/protobuf.
OTEL_EXPORTER_OTLP_INSECUREfalseUse plaintext for an endpoint given without a scheme. An explicit http:// or https:// scheme always wins.
OTEL_EXPORTER_OTLP_HEADERSNot setComma-separated key=value headers sent with every export, such as an API key. Values are percent-decoded.
OTEL_EXPORTER_OTLP_{TRACES,METRICS,LOGS}_ENDPOINTNot setPer-signal endpoint, overriding the generic one. For HTTP, used as given unless it has no path, in which case /v1/traces, /v1/metrics, or /v1/logs is added.
OTEL_EXPORTER_OTLP_{TRACES,METRICS,LOGS}_PROTOCOLGeneric valuePer-signal protocol.
OTEL_EXPORTER_OTLP_{TRACES,METRICS,LOGS}_INSECUREGeneric valuePer-signal plaintext setting.
OTEL_EXPORTER_OTLP_{TRACES,METRICS,LOGS}_HEADERSNot setPer-signal headers, merged over the generic ones.
OTEL_SERVICE_NAMEdapr-mcp-serverservice.name resource attribute.
OTEL_SERVICE_VERSIONBinary versionservice.version resource attribute.
OTEL_METRIC_EXPORT_INTERVAL10000Metric export interval in milliseconds. Go durations such as 30s are also accepted.
OTEL_LOG_EXPORT_INTERVAL5000Log export interval in milliseconds. Go durations are also accepted.
DAPR_MCP_SERVER_METRICS_ENABLEDtrueSet to false to stop exporting metrics while keeping traces.
DAPR_MCP_SERVER_LOGS_OTEL_ENABLEDtrueSet to false to stop exporting logs over OTLP. Logs are still written to stderr.

3 - Authenticating clients of the Dapr MCP server

Require OIDC, SPIFFE, or Dapr Sentry tokens on the Dapr MCP server’s HTTP transport

The Dapr MCP server can require a valid token on every MCP request it serves over streamable HTTP. Authentication is off by default. Set AUTH_MODE to turn it on:

AUTH_MODEAccepts
Not set, or disabledAny request. Use only on localhost.
oidcID or access tokens (JWTs) from an OpenID Connect provider
spiffeSPIFFE JWT-SVIDs, validated with trust bundles from the SPIFFE Workload API
dapr-sentryJWTs issued by Dapr Sentry for a Dapr app
hybridAny combination of the three above

Authentication only applies to the HTTP transport. Over stdio, the MCP client starts the server as a local process, and there is no network listener to protect.

The server checks the settings for the selected mode at startup. If a required variable is missing or a value can’t be parsed, it exits with an error that names the variable. An unrecognized AUTH_MODE value is also rejected at startup.

Sending a token

Clients send the token in the Authorization header, either as Bearer <token> or as the raw token. If DAPR_SENTRY_TOKEN_HEADER names another header, the server checks that header first, in every mode, and expects the raw token there.

A request with no token, or with a token that no enabled method accepts, gets 401 Unauthorized. The server doesn’t say which check failed. Set DAPR_MCP_SERVER_LOG_LEVEL=debug to log the reason on the server.

OIDC

Use oidc for tokens issued to users or applications by an identity provider such as Microsoft Entra ID, Okta, Auth0, Keycloak, or Google.

VariableRequiredDescription
OIDC_ISSUER_URLYesIssuer URL. The server fetches the provider’s discovery document from it at startup, and exits if it can’t.
OIDC_CLIENT_IDYesValue the token’s aud claim must contain.
OIDC_ALLOWED_ALGORITHMSNoSigning algorithms to accept. Default RS256,ES256.
OIDC_SKIP_ISSUER_CHECKNoSkip the iss check. For development only; the server logs a warning when it’s on.
export AUTH_MODE=oidc
export OIDC_ISSUER_URL=https://login.example.com/realms/agents
export OIDC_CLIENT_ID=dapr-mcp-server
dapr run --app-id dapr-mcp-server --resources-path ./components -- dapr-mcp-server --http 0.0.0.0:8080

SPIFFE

Use spiffe for service-to-service calls between workloads that get JWT-SVIDs from a SPIFFE implementation such as SPIRE. The server connects to the Workload API at startup to get trust bundles, waiting up to 10 seconds.

VariableRequiredDescription
SPIFFE_TRUST_DOMAINYesTrust domain, for example example.org. Tokens from other trust domains are rejected.
SPIFFE_SERVER_IDYesThis server’s SPIFFE ID, for example spiffe://example.org/dapr-mcp-server. Callers must request their JWT-SVID with this ID as the audience.
SPIFFE_ENDPOINT_SOCKETNoWorkload API address, for example unix:///run/spire/sockets/agent.sock.
SPIFFE_ALLOWED_CLIENTSNoComma-separated SPIFFE IDs allowed to call the server. Each must be in the trust domain. When not set, any workload in the trust domain is accepted.
export AUTH_MODE=spiffe
export SPIFFE_TRUST_DOMAIN=example.org
export SPIFFE_SERVER_ID=spiffe://example.org/dapr-mcp-server
export SPIFFE_ENDPOINT_SOCKET=unix:///run/spire/sockets/agent.sock
export SPIFFE_ALLOWED_CLIENTS=spiffe://example.org/ns/agents/sa/planner

Dapr Sentry

Use dapr-sentry when the callers are Dapr apps. Dapr Sentry can issue each app a JWT whose subject is the app’s SPIFFE ID, and publish the signing keys as a JWKS. To turn this on in Sentry, enable JWT issuing and the OIDC server, using the Sentry Helm values shown in Authenticating with a Federated Identity Credential. The Microsoft Entra ID steps on that page don’t apply. The JWKS is served at /jwks.json on the Sentry OIDC port. Each calling app requests a token for the audience you set in DAPR_SENTRY_AUDIENCE with the dapr.io/sentry-request-jwt-audiences annotation, or the --sentry-request-jwt-audiences flag in self-hosted mode.

An MCPServer resource with auth.spiffe.jwt sends such a token on every call, so this mode pairs naturally with declaring the Dapr MCP server as an MCPServer.

VariableRequiredDescription
DAPR_SENTRY_JWKS_URLYesURL of the Sentry JWKS.
DAPR_SENTRY_TRUST_DOMAINYesTrust domain of the caller’s SPIFFE ID, for example public. The sub claim must be a SPIFFE ID in this trust domain with a workload path.
DAPR_SENTRY_AUDIENCEYesValue the token’s aud claim must contain. Use the audience your callers request their tokens for.
DAPR_SENTRY_ISSUERNoExpected iss claim. When not set, the issuer isn’t checked.
DAPR_SENTRY_TOKEN_HEADERNoHeader that carries the raw token. Default Authorization. Applies in every mode; see Sending a token.
DAPR_SENTRY_JWKS_REFRESH_INTERVALNoHow often to refresh the JWKS. Default 5m, minimum 30s.
export AUTH_MODE=dapr-sentry
export DAPR_SENTRY_JWKS_URL=https://dapr-sentry.dapr-system.svc.cluster.local:9080/jwks.json
export DAPR_SENTRY_TRUST_DOMAIN=public
export DAPR_SENTRY_AUDIENCE=mcp://dapr-mcp-server
export DAPR_SENTRY_ISSUER=https://sentry.example.com

The server fetches the JWKS at startup and exits if it can’t. Afterwards it refreshes the keys on the configured interval, and also when a token arrives signed with a key it doesn’t have, at most once every 30 seconds. If Sentry can’t be reached, the server keeps using the cached keys for up to 24 hours. Only asymmetric signing algorithms are accepted, the token must have an exp claim, and exp, nbf, and iat are checked with one minute of clock-skew leeway.

Hybrid

hybrid accepts tokens from more than one method. Turn on each method you want with its *_ENABLED variable, and set that method’s required variables. At least one method must be on.

export AUTH_MODE=hybrid

export OIDC_ENABLED=true
export OIDC_ISSUER_URL=https://login.example.com/realms/agents
export OIDC_CLIENT_ID=dapr-mcp-server

export DAPR_SENTRY_ENABLED=true
export DAPR_SENTRY_JWKS_URL=https://dapr-sentry.dapr-system.svc.cluster.local:9080/jwks.json
export DAPR_SENTRY_TRUST_DOMAIN=public
export DAPR_SENTRY_AUDIENCE=mcp://dapr-mcp-server

The server tries the enabled methods in the order OIDC, SPIFFE, Dapr Sentry, and accepts the request as soon as one of them validates the token. The *_ENABLED variables are ignored in single-method modes.

Unauthenticated paths

The health endpoints /livez, /readyz, and /startupz are always served without authentication, as is /dapr/subscribe, which only tells the sidecar the server has no subscriptions. Every other path is MCP and needs a token. There is no setting to exempt more paths.

4 - Dapr MCP server tool reference

Every tool the Dapr MCP server exposes, its inputs, its safety properties, and the component type that enables it

The Dapr MCP server exposes 17 tools. Three are always registered. The rest are registered only while the sidecar has at least one component of the matching type, so an agent never sees tools it can’t use.

The schema the server sends when a client connects is the authoritative definition of each tool. This page is a readable summary of it.

Call get_components first

Component-specific tools take a component name as input, such as storeName or pubsubName. An agent should call get_components first to learn the names that exist, rather than guess. The server’s instructions to the model say the same thing, and tell it to pass metadata fields as JSON objects ({}), never as strings ("{}").

Safety properties

Each tool carries the MCP annotations readOnlyHint, destructiveHint, and idempotentHint, which MCP clients can use to decide whether to ask a person before a call. The tables below show them as:

  • Read-only: reads data and changes nothing.
  • Idempotent: calling it again with the same inputs has no further effect, so it is safe to retry.
  • Destructive: may delete or overwrite data, or trigger an action that can’t be undone. Consider asking a person to confirm the first call.
  • Side effect: changes state or triggers an action somewhere.

Every tool except get_components also sets openWorldHint, because it reaches systems outside the server.

Tools at a glance

ToolRegistered when the sidecar hasSafety
get_componentsAlwaysRead-only, idempotent
invoke_serviceAlwaysDestructive, side effect, not idempotent
invoke_actor_methodAlwaysDestructive, side effect, not idempotent
save_stateA state.* componentSide effect, idempotent
get_stateA state.* componentRead-only, idempotent
delete_stateA state.* componentDestructive, idempotent
execute_transactionA state.* componentDestructive, side effect, not idempotent
publish_eventA pubsub.* componentSide effect, not idempotent
publish_event_with_metadataA pubsub.* componentSide effect, not idempotent
invoke_output_bindingA bindings.* componentDestructive, side effect, not idempotent
get_secretA secretstores.* componentRead-only, idempotent
get_bulk_secretsA secretstores.* componentRead-only, idempotent
converse_with_llmA conversation.* componentRead-only, idempotent
encrypt_dataA crypto.* componentDestructive, side effect, not idempotent
decrypt_dataA crypto.* componentRead-only, idempotent
acquire_lockA lock.* componentSide effect, idempotent
release_lockA lock.* componentSide effect, not idempotent

Tools follow the components loaded in the sidecar. When component hot reloading adds the first component of a type, the server registers that type’s tools the next time a client lists tools or calls get_components, and notifies connected clients that the tool list changed. When the last one is removed, its tools are removed too. Clients that read the tool list only once need to reconnect to see the change.

A tool that fails, because an input is missing or the sidecar returns an error, returns a result marked as an error with a message the model can read, rather than failing the MCP request.

Metadata

get_components

Lists the components loaded in the sidecar, with each one’s name, type, version, and capabilities. Only component types the server has tools for are listed. The list is read live from the sidecar on every call.

Inputs: none.

Service invocation

invoke_service

Calls a method on another Dapr app through service invocation and returns the response body.

InputRequiredDescription
appIDYesApp ID of the target app.
methodYesMethod or path to call, for example orders/status.
dataNoRequest body, usually JSON.
httpVerbNoGET, HEAD, POST, PUT, PATCH, DELETE, or OPTIONS. Default POST.
contentTypeNoContent type of data. Default application/json if data is valid JSON, text/plain otherwise.
metadataNoHeaders to send to the target app. Keys starting with dapr-, grpc-, or : are rejected.

Actors

invoke_actor_method

Calls a method on a virtual actor and returns its response.

InputRequiredDescription
actorTypeYesRegistered actor type.
actorIDYesID of the actor instance.
methodYesActor method to call.
dataNoPayload to pass to the method.

State management

save_state

Saves one key-value pair to a state store.

InputRequiredDescription
storeNameYesState store component name.
keyYesKey to save under.
valueYesValue to save, as a string. JSON is stored as given.

get_state

Reads the value of one key. Reports found: false when the key doesn’t exist.

InputRequiredDescription
storeNameYesState store component name.
keyYesKey to read.

delete_state

Deletes one key.

InputRequiredDescription
storeNameYesState store component name.
keyYesKey to delete.

execute_transaction

Runs several saves and deletes as one atomic transaction. The state store must support transactions.

InputRequiredDescription
storeNameYesState store component name.
itemsYesNon-empty list of operations. Each has a key (required), a value to save, and isDelete: true to delete the key instead.

Publish and subscribe

publish_event

Publishes a message to a topic on a pub/sub component.

InputRequiredDescription
pubsubNameYesPub/sub component name.
topicYesTopic to publish to.
messageYesMessage payload, usually JSON.
contentTypeNoContent type of message. Default application/json if message is valid JSON, text/plain otherwise.

publish_event_with_metadata

Same as publish_event, with publish metadata such as ttlInSeconds.

InputRequiredDescription
pubsubNameYesPub/sub component name.
topicYesTopic to publish to.
messageYesMessage payload, usually JSON.
contentTypeNoContent type of message.
metadataNoPublish metadata, for example {"ttlInSeconds": "60"}.

Bindings

invoke_output_binding

Invokes an operation on an output binding, such as an HTTP endpoint, a queue, or object storage, and returns the response.

InputRequiredDescription
bindingNameYesBinding component name.
operationYesOperation supported by the binding, for example create, get, or delete.
dataNoPayload, usually JSON.
metadataNoMetadata the binding needs for this operation, for example key for a storage binding.

Secrets

Secret values are returned to the model in the tool result. Expose only secret stores the agent should read, and narrow them with secret scopes.

get_secret

Reads one secret from a secret store.

InputRequiredDescription
storeNameYesSecret store component name.
secretNameYesName of the secret.
metadataNoStore-specific options, for example version_id.

get_bulk_secrets

Reads every secret the app can access in a secret store. The tool description tells the model to use it only when the user explicitly asks for all secrets.

InputRequiredDescription
storeNameYesSecret store component name.
metadataNoStore-specific options.

Conversation

converse_with_llm

Sends a prompt to another LLM through a conversation component and returns the reply, along with a context_id to continue the conversation.

InputRequiredDescription
nameYesConversation component name.
promptYesPrompt to send.
contextIdNocontext_id from an earlier call, to continue that conversation. A new one is generated when omitted.
temperatureNoSampling temperature from 0.0 to 1.0. Default 0.7.

Cryptography

encrypt_data

Encrypts text with a key held by a cryptography component and returns the cipher text, base64-encoded.

InputRequiredDescription
componentNameYesCryptography component name.
plainTextYesText to encrypt.
keyNameNoKey name, or name/version. Default rsa-private-key.pem.
keyWrapAlgorithmNoKey wrap algorithm, for example RSA, RSA-OAEP-256, or A256KW. Default RSA.

decrypt_data

Decrypts cipher text produced by encrypt_data and returns the plain text.

InputRequiredDescription
componentNameYesCryptography component name.
cipherTextYesBase64-encoded cipher text.
keyNameNoKey name, or name/version. When omitted, the key named in the cipher text header is used.

Distributed lock

Always pair acquire_lock with release_lock, and set an expiry so a lock isn’t held forever if the agent stops.

acquire_lock

Tries to acquire a distributed lock on a resource. If another owner holds it, the call succeeds with lock_acquired: false.

InputRequiredDescription
storeNameYesLock store component name.
resourceIDYesName of the resource to lock.
lockOwnerYesUnique ID of the caller, used again to release the lock.
expiryInSecondsYesLock lifetime in seconds, greater than zero. The lock expires automatically after this time.

release_lock

Releases a lock. Fails if the lock doesn’t exist or belongs to a different owner.

InputRequiredDescription
storeNameYesLock store component name.
resourceIDYesName of the locked resource.
lockOwnerYesThe owner ID used to acquire the lock.

5 - Dapr MCP server observability

Traces, metrics, and logs the Dapr MCP server exports over OpenTelemetry, and its health endpoints

The Dapr MCP server exports traces, metrics, and logs over the OpenTelemetry Protocol (OTLP), and serves health endpoints for probes when it runs over HTTP.

Turn on telemetry

Telemetry is off until you set an OTLP endpoint. Point the server at an OpenTelemetry Collector, or any backend that accepts OTLP:

export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317
export OTEL_SERVICE_NAME=dapr-mcp-server
dapr run --app-id dapr-mcp-server --resources-path ./components -- dapr-mcp-server --http localhost:8080

An endpoint without a scheme, such as otel-collector:4317, uses TLS. Add OTEL_EXPORTER_OTLP_INSECURE=true to send plaintext to an endpoint like that, or give the scheme explicitly. To use OTLP over HTTP instead of gRPC, set OTEL_EXPORTER_OTLP_PROTOCOL=http/protobuf and use the HTTP port, usually 4318.

All three signals go to the same endpoint unless you override one with its OTEL_EXPORTER_OTLP_{TRACES,METRICS,LOGS}_* variables. See the configuration reference for every setting. If the exporters can’t be set up, the server logs a warning and keeps running without telemetry.

For a collector to receive the data, see Using OpenTelemetry Collector.

Traces

The server creates:

  • A server span for each HTTP request, named after the method and route, for example POST /. It continues the caller’s trace when the request carries a W3C traceparent header.
  • A span for each tool call, named after the tool, for example save_state. It has the attributes mcp.tool.name, mcp.tool.package, and, where the tool targets a component, dapr.component.name, plus details such as the state key or topic. Failed calls are marked with an error status.

The tool span’s trace context is passed to the Dapr sidecar with each gRPC call, so spans from the sidecar, and from any app it calls, join the same trace when Dapr tracing exports to the same backend.

Metrics

Metrics are exported every 10 seconds by default (OTEL_METRIC_EXPORT_INTERVAL). Set DAPR_MCP_SERVER_METRICS_ENABLED=false to turn them off while keeping traces.

MetricTypeUnitDescription
dapr-mcp-server.tool.invocationsCounter{invocation}Tool calls, by outcome.
dapr-mcp-server.tool.errorsCounter{error}Tool calls that failed.
dapr-mcp-server.tool.durationHistogrammsTool call duration.
dapr-mcp-server.tool.in_progressUp-down counter{tool}Tool calls running now.
dapr-mcp-server.http.requests_totalCounter{request}MCP HTTP requests.
dapr-mcp-server.http.request_durationHistogrammsMCP HTTP request duration. Server-sent event streams are counted but not timed, because their duration is the client’s session length.
dapr-mcp-server.http.requests_in_flightUp-down counter{request}MCP HTTP requests being handled now.

Tool metrics carry only bounded attributes: tool.name and tool.package, plus outcome (success or error) on the invocation and duration metrics and error.type on the error counter. Values the agent supplies, such as component names, app IDs, and actor types, are kept off metrics and recorded on the tool’s span instead. HTTP metrics carry http.request.method, http.response.status_code, and http.route. The HTTP metrics cover MCP requests only, not the health endpoints.

Logs

The server writes structured JSON logs to stderr, never stdout, so logs can’t corrupt the stdio transport. Every record includes the service name and version. Set the level with DAPR_MCP_SERVER_LOG_LEVEL (debug, info, warn, or error; default info).

When an OTLP endpoint is set, the same records are also exported as OpenTelemetry logs, correlated with the active trace. Set DAPR_MCP_SERVER_LOGS_OTEL_ENABLED=false to keep logs on stderr only.

At debug level the server logs incoming request headers, with Authorization, Cookie, X-Api-Key, and the configured token header redacted. Each successful tool call is logged at info, and each failure at warn, with its target, such as the store name and key, but never with payloads or secret values.

Health endpoints

With --http, the server serves three endpoints on the same address as MCP. They never require authentication, and each returns JSON with a status of healthy or unhealthy and the server version.

EndpointReturns 200 whenOtherwise
/livezThe process is running.—
/startupzStartup has finished: the server connected to the sidecar and registered its tools.503
/readyzThe server is ready and the Dapr sidecar answers a metadata request within 5 seconds. The response lists each check.503
{
  "status": "healthy",
  "checks": [
    { "status": "healthy", "component": "dapr", "message": "sidecar connected", "latency": "1.2ms" }
  ],
  "version": "v0.0.1"
}

On SIGTERM or SIGINT, /readyz starts returning 503, open server-sent event streams are closed, and in-flight requests get up to 15 seconds to finish before the server exits.

The --health-check flag runs the same liveness check from the command line. It requests /livez on the address from --health-check-addr, or from --http, or localhost:8080, and exits with 0 or 1. The container image uses it as its HEALTHCHECK.

Over stdio there is no HTTP listener, so these endpoints aren’t available.