macp MCP server
Commit Nov 8, 2026Enables MCP clients to run or join governed decision sessions with verifiable commitments using the Multi-Agent Coordination Protocol.
Also known as multiagentcoordinationprotocol/macp-mcp
- Stars
- 0
- Tools
- 8
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 8, 2026
- License
- Apache-2.0
What is macp MCP?
macp enables MCP clients to run or join governed decision sessions with verifiable commitments using the Multi-Agent Coordination Protocol. It exposes 8 tools, such as start_session, propose, vote.
Summary generated from the project's README
About macp MCP server
Managing multi-agent tool use through governed decision sessions is what macp-mcp enables for developers using clients like Claude Desktop, Claude Code, or Cursor. It acts as an interface between an MCP client and a MACP runtime, allowing models to propose, vote on, and commit to specific actions. This ensures that tool execution is not just decided by a model, but is subject to verifiable membership and identity rules enforced by the runtime.
Users can run this server locally using a Dockerized MACP runtime or connect to a production environment using a bearer token. The server provides specific tools such as start_session, propose, vote, and commit to manage the lifecycle of a decision. It also includes a gate mode that acts as a proxy, intercepting tool calls from an upstream server and requiring a quorum or decision session before allowing the call to proceed. This creates a verifiable audit trail through RFC-MACP-0013 hashes for every outcome.
What you can do with it
- 1Coordinate multi-agent deployment decisionsAn AI agent can initiate a session to propose a specific rollout plan and collect votes from other participants.
- 2Enforce tool use policiesDevelopers can use the gate proxy to ensure sensitive tools like file writing only execute after a quorum of approvers agrees.
- 3Verify decision outcomesYou can recompute a commitment hash to ensure the recorded decision has not been tampered with.
Written from the project's README. Every use case is checked against a quote from it.
macp MCP tools 8
Detected from the READMEstart_sessionproposevoteget_commitmentverifyevaluatecommitget_session
| start_session | — | |
| propose | — | |
| vote | — | |
| get_commitment | — | |
| verify | — | |
| evaluate | — | |
| commit | — | |
| get_session | — |
Configuration
MACP_AGENT_IDMACP_ALLOW_INSECUREMACP_AUTH_TOKENMACP_RUNTIME_TARGET
| Name | Description | |
|---|---|---|
| MACP_AGENT_ID | — | |
| MACP_ALLOW_INSECURE | — | |
| MACP_AUTH_TOKEN | — | |
| MACP_RUNTIME_TARGET | — |
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablemultiagentcoordinationprotocol/macp-mcp is public and reachablegithub.com/multiagentcoordinationprotocol/macp-mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-08github.com/multiagentcoordinationprotocol/macp-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model8 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubmacp-mcp
An MCP server that lets any MCP client (Claude Desktop, Claude Code, Cursor and others) run or join a MACP Decision session.
The first proof that MACP governs MCP tool use. MCP decides which tools a
model can call. MACP decides who may use them and when, and records what was
decided. The model drives every step through ordinary MCP tool calls. The MACP
runtime enforces who may propose, vote and commit, ends the session in one
binding Commitment, and gives that outcome an RFC-MACP-0013 hash that anyone
can recompute.
examples/decision-via-mcp.md is a recorded
run: two MCP clients drive a session to RESOLVED. The runtime refuses the
non-initiator's commit call, and the commitment hash verifies.
MCP client (model) ──stdio──▶ macp-mcp ──gRPC──▶ MACP runtime
tool calls one MACP agent enforces membership, order,
(macp-sdk-python) identity; records the Commitment
Install
pip install macp-mcp # or: uvx macp-mcp
Python 3.11 or newer. It needs a MACP runtime to talk to. For local development:
docker run -p 50051:50051 -e MACP_ALLOW_INSECURE=1 -e MACP_MEMORY_ONLY=1 \
ghcr.io/multiagentcoordinationprotocol/macp-runtime:0.14.1
One macp-mcp process is one MACP agent. To have several agents take part in
a session, run one server per agent (for example, one per MCP client), each
with its own MACP_AGENT_ID.
Configure your MCP client
Claude Desktop
Add the server to claude_desktop_config.json (Settings → Developer → Edit Config):
{
"mcpServers": {
"macp": {
"command": "uvx",
"args": ["macp-mcp"],
"env": {
"MACP_RUNTIME_TARGET": "127.0.0.1:50051",
"MACP_AGENT_ID": "coordinator",
"MACP_ALLOW_INSECURE": "1"
}
}
}
}
If you installed with pip, use "command": "macp-mcp" and drop args.
Claude Code
claude mcp add macp \
--env MACP_RUNTIME_TARGET=127.0.0.1:50051 \
--env MACP_AGENT_ID=coordinator \
--env MACP_ALLOW_INSECURE=1 \
-- uvx macp-mcp
Or check it into a project's .mcp.json:
{
"mcpServers": {
"macp": {
"command": "uvx",
"args": ["macp-mcp"],
"env": {
"MACP_RUNTIME_TARGET": "127.0.0.1:50051",
"MACP_AGENT_ID": "alice",
"MACP_ALLOW_INSECURE": "1"
}
}
}
}
Then ask the model something like: "Start a MACP decision with alice on which deployment plan to use, propose a canary rollout, and vote for it."
Against a production runtime
Drop MACP_ALLOW_INSECURE and pass the bearer token the runtime issued for
this agent:
"env": {
"MACP_RUNTIME_TARGET": "macp.example.com:443",
"MACP_AGENT_ID": "coordinator",
"MACP_AUTH_TOKEN": "<token issued for coordinator>"
}
Environment variables
| Variable | Default | Meaning |
|---|---|---|
MACP_RUNTIME_TARGET |
127.0.0.1:50051 |
Runtime gRPC address (host:port). |
MACP_AGENT_ID |
mcp-agent |
The MACP agent this server acts as. With dev-agent auth it is also the bearer token. With MACP_AUTH_TOKEN it is the identity the runtime must bind the token to. |
MACP_AUTH_TOKEN |
unset | Bearer token issued by the runtime. When unset, dev-agent auth is used, which needs a runtime started with MACP_ALLOW_INSECURE=1. |
MACP_ALLOW_INSECURE |
off | 1 uses plaintext gRPC. For a local runtime only. |
MACP_TLS_CA_FILE |
system trust | PEM bundle for a private CA. Cannot be combined with MACP_ALLOW_INSECURE. |
MACP_DEFAULT_TTL_MS |
300000 |
Session TTL used when start_session is called without ttl_ms. |
MACP_REPLAY_IDLE_MS |
1000 |
How long a history read waits for the next envelope before treating the replay as complete. |
The server logs to stderr only, because stdout carries the MCP protocol. A bad configuration exits with status 2 and a one-line message.
Tools
| Tool | Kind | What it does |
|---|---|---|
start_session |
write | Start a Decision session with this agent as initiator. Takes intent, participants and optional ttl_ms and context_id. Returns the session_id to share. |
propose |
write | Put an option (proposal_id, option, rationale) up for decision. |
vote |
write | Cast this agent's APPROVE / REJECT / ABSTAIN vote on a proposal. |
get_commitment |
read | The resolved session's binding Commitment, the exact payload bytes (payload_b64) and its RFC-MACP-0013 commitment_hash. |
verify |
read | Recompute a commitment hash with the SDK verifier, either from the runtime's recorded history (session_id) or from bytes you hold (payload_b64). Returns match, mismatch or cannot_verify. |
evaluate |
write | Record a scored assessment (APPROVE / REVIEW / BLOCK / REJECT, confidence 0..1) before voting. |
commit |
write | Resolve the session with a binding Commitment (action, authority_scope, reason). Under the default policy only the initiator can commit. |
get_session |
read | The session's state, participants, proposals, evaluations, votes, approve totals and majority winner. |
The first five are the core loop: start, propose, vote, read the outcome and check it. The other three are the minimum needed to make that loop usable from MCP:
commit: a Decision session only resolves, and only produces a Commitment forget_commitmentandverifyto read, when someone commits. Without this tool an MCP client could never finish a session it started.get_session: MCP is request/response, and the runtime'sGetSessionreturns metadata only. Without this tool a model joining a session has no way to see what was proposed or how the votes stand. It rebuilds the session view from the runtime's replayable history.evaluate: the Decision mode's assessment step. It lets an agent record a reasoned, scored opinion (including aBLOCK) that other participants and later auditors can see, separately from the bare vote.
Objections, cancellation, signals and other modes are deliberately left out. They belong to orchestrators built on macp-sdk-python.
Errors the model can act on, such as a runtime rejection or a bad argument,
come back as tool errors with the text "<CODE>: <message>", for example
FORBIDDEN: Forbidden when a non-initiator tries to commit. The code is the
MACP error code (the Ack failure code, then the macp-error-code trailer,
then the gRPC status name).
The server is stateless. Every read replays the session from the runtime, so a restart loses nothing, and several servers (agents) can share one session.
Gate an MCP server's tool calls (macp-mcp gate)
macp-mcp gate is an MCP proxy. Put it in front of any stdio MCP server, and
the tool calls you name in a policy file run only after a MACP session
approves them:
macp-mcp gate --policy gate.json --upstream npx -y @modelcontextprotocol/server-filesystem /srv
Everything after --upstream is the upstream's command line. Your MCP client
spawns the gate instead of the upstream. The gate lists the upstream's tools
unchanged.
{
"version": 1,
"server": "filesystem",
"rules": [
{ "tool": "write_file", "mode": "macp.mode.quorum.v1",
"participants": ["alice", "bob", "carol"], "threshold": 2, "ttl_ms": 120000 },
{ "tool": "move_*", "mode": "macp.mode.decision.v1",
"participants": ["alice", "bob"], "ttl_ms": 60000 }
]
}
A tools/call that matches no rule is forwarded as-is. The first rule that
matches (* and ? are wildcards) makes the gate, acting as MACP agent
MACP_AGENT_ID, do this:
-
Open a Quorum or Decision session with the rule's
participantsas approvers. Itscontext_idissha256:plus the hex SHA-256 of the RFC 8785 canonical JSON of{arguments, server, tool}, which binds the session to this exact call. The approvers find it by thatcontext_id(ListSessions/WatchSessions) and vote with any MACP client. -
Commit as soon as the outcome is settled: approve once
thresholdapprovers (default: a strict majority) have approved, deny once that can no longer happen. Each approver's first ballot counts. -
Approved: forward the call. The upstream's result comes back with the Commitment attached, next to any
_metathe upstream set:"_meta": { "io.multiagentcoordinationprotocol/commitment": { "session_id": "…", "mode": "macp.mode.quorum.v1", "outcome": "approve", "commitment_hash": "sha256:…" } }commitment_hashis the RFC-MACP-0013 hash. Check it with theverifytool or any MACP SDK. -
Refused: return a tool error and never call the upstream. The error starts with
POLICY_DENIED(the approvers denied it, or a runtime policy refused the commitment) orSESSION_NOT_OPEN(the session expired or was cancelled first). An argument holding an integer outside ±(2^53−1) is refused withINVALID_ARGUMENTbefore any session opens, because it has no canonical form to bind.
The gate passes its environment on to the upstream, minus MACP_AUTH_TOKEN.
examples/gated-tool-call.md is a recorded run
against the pinned runtime: one passthrough, one approved write, one rejected
write and one expired delete.
contract/gate/ pins the policy schema, the CLI, the session
shape, the refusal texts and the context_id vectors. The TypeScript twin
uses a byte-identical copy.
Binding a runtime policy (policy_version)
A rule can bind the session, through policy_version, to an RFC-MACP-0012
policy registered on the runtime. Set the rule's threshold to at least the
bound policy's threshold. The gate commits on its own tally, so with a lower
rule threshold it commits early and the runtime refuses the Commitment:
- Decision: the refusal is
POLICY_DENIED: <runtime message>. - Quorum: macp-runtime 0.14.0 applies a policy threshold inside the mode's
commitment-readiness check, so the refusal is
INVALID_ENVELOPE(an invalid payload), notPOLICY_DENIED.
In both modes the gate fails safe. The call is refused after the first
approval, the upstream is never called, and the gate cancels the session
(CANCELLED). The note under policy_binding in
contract/gate/session.json records the same
behaviour. Integration tests pin it against runtime 0.14.0:
tests/integration/test_gate_policy.py
(added in #12)
and the TypeScript twin's
gate-policy.test.ts
(#10).
Tool contract
contract/tools.json pins the tool names,
descriptions, annotations, input schemas and output schemas. It is fully
inlined JSON Schema 2020-12. The TypeScript twin
(macp-mcp-typescript)
exposes the identical surface and tests against a byte-identical copy of this
file. Any change to the tool surface changes the manifest (make contract)
and needs the matching change in the TypeScript twin.
Development
make setup # pip install -e ".[dev]"
make lint typecheck test # ruff, mypy strict, unit tests + 85% coverage gate
make verify-contract # advertised tools == contract/tools.json; gate contract checks
make test-integration-docker # CI's integration gate: pinned runtime image + stdio MCP clients
make transcript # re-record examples/*.md transcripts (runtime on :50051)
Releases follow macp-sdk-python: release-please opens the release PR, and
merging it tags vX.Y.Z, which publishes to PyPI through trusted publishing.
License
Apache-2.0
macp MCP questions
What tools does macp MCP provide?
It exposes 8 tools, including start_session, propose, vote, get_commitment, verify.
What does MACP do for MCP tool use?
While MCP decides which tools a model can call, MACP decides who may use them and when, and records the decision.
Can I use this to restrict specific tool calls?
Yes, you can use the 'macp-mcp gate' proxy to require a MACP session approval for specific tools defined in a policy file.
How do I verify a decision outcome?
You can use the verify tool to recompute a commitment hash from the runtime's recorded history or from provided payload bytes.
Is the server stateful?
No, the server is stateless because every read replays the session from the runtime.