Rabbitmq

RabbitMQ Management HTTP API MCP (Model Context Protocol) server, generated by mcpify.

Sponsor

Building and maintaining this took real ideation, time, design effort, and compute (including LLM usage) to get right. If it's useful to you, consider sponsoring its development — any amount helps keep it going. 💛

Exposes exactly 3 tools — search, get, call — backed by an embedded semantic database (mcp_store.db), so an LLM never needs the full API surface in context. The default RabbitMQ 4.3.2 store contains 137 real Management HTTP API operations: 93 GET, 20 DELETE, 12 PUT, and 12 POST. It also exposes MCP prompts: a master rabbitmq menu plus 11 guided sub-workflows for common multi-step RabbitMQ management tasks — see Workflows below.

Install

cargo build --release

This builds three binaries into target/release/: rabbitmq-mcp (the CLI/server below), rabbitmq-mcp-populate-embeddings, and rabbitmq-mcp-healthcheck. Run cargo install --path . instead if you want rabbitmq-mcp on your PATH so the commands below work without a target/release/ prefix.

Prebuilt binaries for macOS, Linux, and Windows are attached to each GitHub Release, along with a shell/PowerShell installer script.

Or install the published crate directly:

cargo install rabbitmq-mcp

Setup

cargo run -- setup

Interactively collects the API URL and the credentials your chosen auth method needs, then lets you persist them as a .env file, a local (./rabbitmq-mcp.config.yml) or global (~/.rabbitmq-mcp/config.yml) YAML config file, or a ready-to-run CLI invocation.

Supported auth methods: basic (username/password).

Configuration

Env var	Purpose
RABBITMQ_MCP_URL	Base URL of the target API.
RABBITMQ_MCP_USERNAME / RABBITMQ_MCP_PASSWORD	Overrides any stored credential for basic auth — set both to authenticate without running setup first (checked before the OS keychain/encrypted-file fallback).
RABBITMQ_MCP_LOG_LEVEL	Log verbosity (trace/debug/info/warn/error).

See .env.example for the full list of supported variables.

No base-URL suffix is needed here — this API's paths already include /api, and the OpenAPI spec has no servers[] entry to derive one from. For a local RabbitMQ installation, RABBITMQ_MCP_URL is usually http://127.0.0.1:15672.

Usage

Terminal Client (default)

# 1. Semantic search over all 137 operations in the default RabbitMQ store
rabbitmq-mcp search "list queues" --limit 3

# 2. Inspect the exact method, path, and input/output schemas before calling
rabbitmq-mcp get getApiQueuesVhost
# method: GET
# path: /api/queues/{vhost}

# 3. Path and query parameters are fields in one --args JSON object
rabbitmq-mcp call getApiQueuesVhost --args '{"vhost":"/"}'

call accepts one JSON object through --args (or -a), not arbitrary per-operation CLI flags. Use get <operationId> to see the accepted field names and which ones are required.

Other subcommands: rabbitmq-mcp test-connection (verify the configured API URL/credentials are reachable), rabbitmq-mcp config (print the resolved configuration, secrets redacted), rabbitmq-mcp version (print the installed version), and rabbitmq-mcp versions (list the API spec versions this project has a store for).

Harness Server

rabbitmq-mcp start                              # stdio transport (default)
rabbitmq-mcp http --host 127.0.0.1 --port 3000  # HTTP transport

Connect an MCP client

stdio: after running rabbitmq-mcp setup, configure an MCP host to spawn the server. Include the connection settings printed by the wizard; this example targets a local RabbitMQ 4.3.2 node:

{
  "mcpServers": {
    "rabbitmq": {
      "command": "rabbitmq-mcp",
      "args": ["start"],
      "env": {
        "RABBITMQ_MCP_URL": "http://127.0.0.1:15672",
        "RABBITMQ_MCP_AUTH_METHOD": "basic",
        "RABBITMQ_MCP_API_VERSION": "4.3.2",
        "RABBITMQ_MCP_TRANSPORT": "stdio"
      }
    }
  }
}

Use the absolute executable path if rabbitmq-mcp is not on the MCP host's PATH. The stdio server reads the connection settings from this env block and uses the credentials saved by setup.

HTTP: every request must include the RabbitMQ Basic Authentication value — HTTP transport intentionally does not fall back to credentials stored on the server:

{
  "mcpServers": {
    "rabbitmq": {
      "url": "http://127.0.0.1:3000/mcp",
      "headers": {
        "Authorization": "Basic <base64-encoded-username-and-password>"
      }
    }
  }
}

Keep the listener on localhost unless you have added appropriate network access controls and TLS in front of it.

Workflows

Beyond the 3 tools, the server also implements the MCP prompts capability (prompts/list / prompts/get, supported by any MCP client that implements prompts): a master rabbitmq prompt that presents a menu of guided, multi-step RabbitMQ management workflows, plus one sub-workflow prompt per topic below. Each sub-workflow walks the calling LLM through the right sequence of search/get/call steps, asks for whatever parameters aren't already known, and gates progress on confirming each step actually worked rather than just issuing the call.

Start with rabbitmq (optionally passing a free-text goal, e.g. "set up a dead letter queue") — it routes to the right sub-workflow below and, where the calling client supports running sub-tasks in an isolated context, hands the whole sub-workflow off to one so its search/get/call trace doesn't fill up the main conversation.

Prompt	Covers
rabbitmq	Master menu; routes to the right sub-workflow based on a goal
rabbitmq-queues	List/create/delete/purge queues, queue actions, messages, rebalance
rabbitmq-exchanges	List/create/delete exchanges, bindings, publish
rabbitmq-bindings	Bind/unbind exchange↔queue and exchange↔exchange
rabbitmq-dead-letter	Guided DLX/DLQ setup, including the create-time-vs-policy decision
rabbitmq-vhosts	Virtual host lifecycle, limits, deletion protection
rabbitmq-users-permissions	User lifecycle, vhost/topic permissions, per-user limits
rabbitmq-policies	Policies and operator-policy overrides
rabbitmq-federation-shovel	Federation upstreams and shovels (configured via generic parameters)
rabbitmq-definitions-backup-restore	Export/import full-cluster or per-vhost definitions
rabbitmq-monitoring-diagnostics	Connections, channels, consumers, streams, health checks, node/cluster status
rabbitmq-upgrade-readiness	Pre-restart/upgrade checks (deprecated features, feature flags, health) and post-restart recovery

This project supports 5 RabbitMQ Management API versions (see Configuration's RABBITMQ_MCP_API_VERSION), and operation availability and even response shape can differ between them — every workflow above is written to describe operations only by what they do (e.g. "search for how to create a queue"), never by a hardcoded operationId or an assumed response field, so the same prompt text stays correct regardless of which version the server is configured for.

Docker

# Stdio: the MCP client launches this one-off process and owns its stdin/stdout pipes
docker compose run --rm -T rabbitmq-mcp

# HTTP: a long-running network endpoint published on http://localhost:3000
docker compose up rabbitmq-mcp-http

Run these commands from the repository root. Docker Compose automatically discovers docker-compose.yml; rabbitmq-mcp and rabbitmq-mcp-http are service names inside that file, not filenames. Writing docker compose -f docker-compose.yml ... is equivalent, but -f is only needed when the file has another name or location, or when combining multiple Compose files.

Both services read configuration from a local .env file (copy .env.example) and persist credentials and configuration under ~/.rabbitmq-mcp on the host. For stdio, -T disables pseudo-TTY allocation so MCP JSON-RPC stays on raw stdin/stdout, and --rm removes the one-off container when the client exits.

Stdio is a process transport, not a listening service: the MCP client must start the server and communicate through that exact child process's stdin/stdout. This is useful when an MCP client is configured to launch docker compose run --rm -T rabbitmq-mcp, in local scripts or CI that directly exchange MCP messages with the process, or in a custom image where your application launches the generated server's start subcommand as a child process. Merely putting the application and server in the same image—or starting the stdio container separately with docker compose up—does not connect their streams. One stdio server process normally serves one client. Use HTTP when independently started applications, multiple clients, another container, or a remote machine need to connect over the network.

Observability & Resilience

Logging

Structured logs go to stderr (never stdout, which is reserved for MCP JSON-RPC frames on stdio transport): JSON by default, pretty-printed automatically when stderr is an interactive TTY (auto-detected — there's no separate flag for this). Level is controlled by RABBITMQ_MCP_LOG_LEVEL (default info), passed straight through to tracing_subscriber::EnvFilter, so directive syntax works too, e.g.:

RABBITMQ_MCP_LOG_LEVEL="rabbitmq_mcp=debug,warn" rabbitmq-mcp start

Secret redaction exists as a helper (core::sanitizer::sanitize, case-insensitive substring match on keys containing password/token/secret/authorization/apikey/api_key/api-key/credential), but today its only caller is rabbitmq-mcp config (which prints the resolved config with those fields redacted). Request/response payloads aren't logged at all currently — the only tracing call sites are lifecycle/error events — so there's no in-flight redaction path exercised in normal operation yet.

OpenTelemetry tracing

An OTLP/HTTP trace exporter (core/otel.rs) is built unconditionally at startup; if it fails to build, tracing export is silently skipped — there's no dedicated on/off switch in this app. It's tracing only (no OTel metrics exporter is wired up — see "Metrics" below). Point it at a collector with the OTLP SDK's own standard env vars (not RABBITMQ_MCP_-prefixed), which opentelemetry-otlp reads directly:

OTEL_EXPORTER_OTLP_ENDPOINT=http://otel-collector:4318 rabbitmq-mcp start

Defaults to http://localhost:4318 if unset. OTEL_EXPORTER_OTLP_TRACES_ENDPOINT, OTEL_EXPORTER_OTLP_HEADERS, _PROTOCOL, _TIMEOUT, and _COMPRESSION are also honored (standard OTLP conventions).

Metrics

Separate from OTel: GET /metrics (HTTP transport only — not available over stdio) serves a minimal hand-rolled Prometheus-text counter store (http/metrics.rs). Today it only tracks one counter, http_requests_total:

curl http://127.0.0.1:3000/metrics
# http_requests_total 4

Circuit breaker, retries, and rate limiting

Every outbound call to the target API (services/api_client.rs) passes through a rate limiter, then a circuit breaker, then the retry loop:

Behavior	Configurable?	Knob	Default
Request timeout	Yes	RABBITMQ_MCP_TIMEOUT_MS / timeout_ms	30000 ms
Retry attempts on request failure	Yes	RABBITMQ_MCP_RETRY_ATTEMPTS / retry_attempts	3 (immediate retry, no backoff/jitter)
Rate limit	Partially	RABBITMQ_MCP_RATE_LIMIT / rate_limit	100 calls; window is hardcoded to 1 second, not configurable
Circuit breaker	No	— (CircuitBreaker::default())	opens after 5 consecutive failures, 30s before a half-open trial call

("Knob" here means an env var or a matching key in rabbitmq-mcp.config.yml/~/.rabbitmq-mcp/config.yml//etc/rabbitmq-mcp/config.yml — see the config cascade in core/config_manager.rs.)

Health checks

GET /healthz (HTTP transport only) reports the status of a ComponentRegistry, refreshed every 30 seconds with a 5-second per-check timeout by a HealthCheckManager — both intervals are hardcoded, not configurable. Today exactly one check is registered, store (can the active mcp_store*.db file be opened), marked critical:

curl http://127.0.0.1:3000/healthz
# {"status":"Healthy","components":1}   # 503 + "Unhealthy" if the critical check is failing

Two related but distinct checks exist:

• rabbitmq-mcp-healthcheck — the standalone binary wired into the Dockerfile's HEALTHCHECK; it only checks that the active store file exists and is readable on disk, and does not talk to a running server or /healthz.
• rabbitmq-mcp test-connection — an on-demand CLI check that the target API itself is reachable with the configured credentials; unrelated to the periodic /healthz checks above.

Credential storage

rabbitmq-mcp setup writes credentials straight to the OS-native secret store via the keyring crate (macOS Keychain / Windows Credential Manager / Linux Secret Service), under service rabbitmq-mcp, account active-credentials. If no OS keychain backend is available (e.g. no D-Bus secret-service daemon in a minimal container), it falls back automatically to an AES-256-GCM-encrypted file at ~/.rabbitmq-mcp/credentials.enc (0600, parent dir 0700 on Unix); the key is derived from $HOME plus the service name, so that file isn't portable to another machine.

The RABBITMQ_MCP_USERNAME/RABBITMQ_MCP_PASSWORD env vars documented in .env.example are read directly by AuthManager::credentials() and take priority over the stored keychain/file credentials — useful for supplying credentials purely via environment (e.g. in a container) without ever running setup.

Credentials are never persisted into the .env/config-file output of setup itself; those files only carry non-secret settings, with credentials always going through the keychain/encrypted-file path.

Testing

cargo test

Coverage

bash scripts/coverage.sh   # generates HTML and fails below 85% production-line coverage

The 85% gate counts executable production lines under src/ and removes inline #[cfg(test)] module bodies from the LCOV denominator, so adding test code cannot inflate the result. The unfiltered annotated HTML remains useful for line-by-line analysis at target/coverage/html/index.html; the gate's machine-readable input is target/coverage/production-lcov.info. The command requires Python 3, cargo-llvm-cov, and the llvm-tools-preview Rust component.

Profiling

bash scripts/profile.sh        # clean CPU profiling via samply
bash scripts/profile-heap.sh   # steady-state heap profiling via dhat-rs

CPU and heap profiling use separate builds: scripts/profile.sh deliberately profiles normal release binaries so DHAT allocation tracking cannot distort CPU samples, while scripts/profile-heap.sh starts DHAT collection only after its warmup search. CPU profiling records profile/cold-start.json.gz from a one-shot CLI search, then attaches to an already-initialized search harness and records profile/warm-search.json.gz; this keeps model initialization from being mistaken for steady-state request cost. Heap profiling defaults to 1 warmup and 5 measured searches, configurable with PROFILE_HEAP_WARMUPS, PROFILE_HEAP_ITERATIONS, and PROFILE_QUERY. Both scripts supply harmless URL/auth defaults when a generated checkout has not been configured because catalog search never calls the generated API. profile/bottleneck-report.md ranks coverage gaps and shows separate cold and warm CPU summaries. Requires samply (cargo install samply).

License

MIT — see LICENSE.

---

Generated by mcpify — do not hand-edit generated files; re-run mcpify against an updated OpenAPI spec instead.