Dapr MCP Server

io.github.daprPublished by GitHub account daprv0.0.3Updated Nov 4, 2026

Dapr state, pub/sub, bindings, secrets, locks, crypto, conversation, actors, invocation as MCP tools

Overview

AI-generated overview

Go MCP server that fronts a Dapr sidecar, exposing state, pub/sub, bindings, secrets, locks, crypto, actors and service invocation as tools for AI agents.

What you can do
  • Inspect the sidecar's components and invoke services or actor methods
  • Read, save, bulk-read, delete and transactionally batch state entries
  • Publish pub/sub events, with or without metadata such as headers and TTL
  • Fetch single or bulk secrets from configured secret stores
  • Encrypt and decrypt data, and acquire or release distributed locks
  • Call output bindings to external systems and delegate prompts to a downstream LLM
When to use it
Useful when an assistant works alongside a Dapr-enabled application and should read or change its state, publish events, call other services or actors, or use Dapr-managed secrets, locks and crypto. Tools appear only for building blocks that exist in the deployment.
Requirements
Runs as a local process next to a Dapr sidecar, started with dapr run; available as a container image, a release binary, or built from source with Go 1.26.6+. Needs the sidecar's gRPC port in DAPR_GRPC_PORT, and DAPR_API_TOKEN if the sidecar requires one. Optional flags switch to streamable HTTP and health checks.
Before you install
Several tools change or remove data: save_state, delete_state, execute_transaction, publish_event, invoke_output_binding, invoke_service and invoke_actor_method act on live systems. get_bulk_secrets is flagged high-risk, and get_secret exposes secret values to the assistant. DAPR_API_TOKEN is a credential. HTTP mode can be exposed remotely and gated by OIDC, SPIFFE or Dapr Sentry.

Installation

In SourceWeft

  1. Open Dapr MCP Server in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

dapr-mcp-server

A Model Context Protocol (MCP) server that exposes Dapr's building blocks as tools for AI agents.

[OpenSSF Scorecard]


What it is

dapr-mcp-server is a Go MCP server that fronts a Dapr sidecar and hands AI agents a curated set of tools over every Dapr building block: state, pub/sub, secrets, service invocation, actors, bindings, distributed locks, cryptography, and conversation components. Tools register dynamically from the live component set — if your deployment has no pub/sub broker, the pub/sub tools aren't exposed.

Two transports are supported: stdio for local IDE integrations (Claude Desktop, Cursor, VS Code, Claude Code) and streamable HTTP for remote or shared deployments. Every tool call is annotated with OpenTelemetry spans, metrics, and optional log export; requests can be gated by OIDC, SPIFFE, Dapr Sentry, or a hybrid of the three.

Full documentation lives at docs.dapr.io / developing-ai / mcp.

Quick start

Run the binary next to a Dapr sidecar with dapr run (install it from Install):

bash
dapr init
# stdio, for local MCP clients that launch the server themselvesdapr run --app-id dapr-mcp-server --resources-path resources -- dapr-mcp-server
# streamable HTTP, for remote clientsdapr run --app-id dapr-mcp-server --resources-path resources -- dapr-mcp-server --http :8080

With --http, connect any MCP client to http://localhost:8080/. The container image is meant for Kubernetes, where the Dapr sidecar injector adds the sidecar through the dapr.io/enabled: "true" and dapr.io/app-id pod annotations. For the complete walk-through (components, auth, OTEL, verification), see the getting started guide.

Install

MethodCommand
Containerdocker pull ghcr.io/dapr/dapr-mcp-server:latest
BinaryDownload from Releases and place on PATH
From source (Go 1.26.6+)go install github.com/dapr/dapr-mcp-server/cmd/dapr-mcp-server@latest

The server is listed in the official MCP Registry as io.github.dapr/dapr-mcp-server, so MCP clients that browse the registry can install it as a container.

Configuration

The configuration guide has the full environment variable reference.

FlagDefaultPurpose
--http <addr>unset (stdio)Serve streamable HTTP on this address instead of stdin/stdout. Health probes are served on /livez, /readyz and /startupz.
--health-checkfalseProbe /livez of a running server and exit 0 if it answers 200, 1 otherwise. Used by the container HEALTHCHECK.
--health-check-addr <host:port>from --http, else localhost:8080Address --health-check probes. A wildcard host such as 0.0.0.0 is probed as localhost.
--versionfalsePrint the version and exit.

Logs are written as JSON to stderr, so they never mix with the stdio transport on stdout. /readyz returns 503 while the Dapr sidecar is unreachable.

Settings specific to the HTTP transport:

Environment variableDefaultPurpose
DAPR_MCP_CORS_ORIGINunset (no CORS headers)Origin allowed to call the server from a browser, for example https://app.example.com. Set it only when a browser-based MCP client on another origin needs access.

Documentation

PagePurpose
OverviewWhat the server is, architecture, capabilities, when to use it
Getting startedInstall, configure components, run, verify
Tool referenceSchemas, inputs, outputs, and safety flags for every tool
ConfigurationEnvironment variables, flags, and transport settings
AuthenticationOIDC, SPIFFE, Dapr Sentry, hybrid mode
ObservabilityTraces, metrics, and logs

AI coding agents contributing to this repo: see AGENTS.md. For human contributors: see CONTRIBUTING.md.

Tools at a glance

All tools, with links to their entries in the tool reference. Core tools are always registered; conditional tools register only when a matching Dapr component exists. The server follows components that Dapr hot-reloads: each time a client lists tools or calls get_components, it checks the sidecar, adds a building block's tools when its first component appears and removes them when its last one goes, and tells connected clients the tool list changed.

CategoryToolRegistrationNotes
metadataget_componentsCoreAlways call first
invokeinvoke_serviceCoreService-to-service HTTP invocation
actorsinvoke_actor_methodCoreVirtual-actor method call
statesave_statestate.*Idempotent save
stateget_statestate.*Read-only
stateget_bulk_statestate.*Read-only; several keys
statedelete_statestate.*Destructive, idempotent
stateexecute_transactionstate.*Atomic batch
pubsubpublish_eventpubsub.*Not idempotent
pubsubpublish_event_with_metadatapubsub.*Adds headers/TTL
bindingsinvoke_output_bindingbindings.*External-system I/O
secretsget_secretsecretstores.*Single secret
secretsget_bulk_secretssecretstores.*High-risk; bulk fetch
conversationconverse_with_llmconversation.*Delegate to a downstream LLM
cryptoencrypt_datacrypto.*RSA encrypt
cryptodecrypt_datacrypto.*RSA decrypt
lockacquire_locklock.*Distributed mutex
lockrelease_locklock.*Pair with acquire_lock

Development

bash
go build -o dapr-mcp-server ./cmd/dapr-mcp-servergo test -race ./...golangci-lint run ./...

See AGENTS.md for the full contributor / AI-agent playbook (build commands, tool-addition pattern, testing strategy, DCO flow).

Contributing

Contributions welcome — open issues via the issue templates, sign your commits per the DCO, and follow the pull request template. See CONTRIBUTING.md for the full workflow.

Security issues: do not open a public issue — follow the Dapr security disclosure process instead.

License

Apache 2.0 — see LICENSE.

Source: README.md at commit 93f9446

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.0.3LatestOct 14, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts