macp MCP server
2026년 11월 8일 커밋Multi-Agent Coordination Protocol을 사용하여 검증 가능한 약속과 함께 관리된 의사결정 세션을 실행하거나 참여할 수 있도록 MCP client를 지원합니다.
다른 이름 multiagentcoordinationprotocol/macp-mcp
- 스타
- 0
- Tools
- 8
- 다운로드, 30일
- —
- 최신 버전
- —
- 마지막 커밋
- 2026년 11월 8일
- 라이선스
- Apache-2.0
macp MCP란?
Multi-Agent Coordination Protocol을 사용하여 검증 가능한 약속과 함께 관리된 의사결정 세션을 실행하거나 참여할 수 있도록 MCP client를 지원합니다. 8개 도구를 제공합니다. 예: start_session, propose, vote.
프로젝트 README에서 생성된 요약
macp MCP server 정보
macp-mcp는 Claude Desktop, Claude Code 또는 Cursor와 같은 client를 사용하는 개발자가 관리된 의사결정 세션을 통해 멀티 에이전트 도구 사용을 관리할 수 있게 합니다. 이는 MCP client와 MACP runtime 사이의 인터페이스 역할을 하며, 모델이 특정 작업을 제안하고, 투표하고, 확정(commit)할 수 있도록 합니다. 이를 통해 도구 실행이 단순히 모델에 의해 결정되는 것이 아니라, 런타임에 의해 강제되는 검증 가능한 멤버십 및 신원 규칙을 따르도록 보장합니다.
사용자는 Docker화된 MACP runtime을 사용하여 이 서버를 로컬에서 실행하거나, bearer token을 사용하여 프로덕션 환경에 연결할 수 있습니다. 서버는 의사결정 수명 주기를 관리하기 위해 start_session, propose, vote, commit과 같은 특정 도구를 제공합니다. 또한 프록시 역할을 하는 gate mode를 포함하고 있어, 상위 서버의 도구 호출을 가로채고 호출을 진행하기 전에 정족수 충족 또는 의사결정 세션을 요구합니다. 이를 통해 모든 결과에 대해 RFC-MACP-0013 hash를 통한 검증 가능한 감사 추적을 생성합니다.
활용 사례
- 1멀티 에이전트 배포 의사결정 조정AI 에이전트가 세션을 시작하여 특정 롤아웃 계획을 제안하고 다른 참여자들로부터 투표를 수집할 수 있습니다.
- 2도구 사용 정책 강제개발자는 gate 프록시를 사용하여 파일 쓰기와 같은 민감한 도구가 승인자 정족수가 동의한 후에만 실행되도록 보장할 수 있습니다.
- 3의사결정 결과 검증commitment hash를 다시 계산하여 기록된 의사결정이 변조되지 않았는지 확인할 수 있습니다.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
macp MCP 도구 8
README에서 감지됨start_sessionproposevoteget_commitmentverifyevaluatecommitget_session
| start_session | — | |
| propose | — | |
| vote | — | |
| get_commitment | — | |
| verify | — | |
| evaluate | — | |
| commit | — | |
| get_session | — |
구성
MACP_AGENT_IDMACP_ALLOW_INSECUREMACP_AUTH_TOKENMACP_RUNTIME_TARGET
| 이름 | 설명 | 유형 |
|---|---|---|
| MACP_AGENT_ID | — | |
| MACP_ALLOW_INSECURE | — | |
| MACP_AUTH_TOKEN | — | |
| MACP_RUNTIME_TARGET | — |
자동 검사
2026년 11월 14일에 실행됨전체 보고서 →아직 인증되지 않았습니다. 서버는 80점 이상의 점수, 심각한 결함 없음, 그리고 검사에 충분한 데이터를 갖추어야 합니다. 검사 방식 · 점수를 높이기 위해 수정할 항목
- 소스 저장소 연결 및 접근 가능multiagentcoordinationprotocol/macp-mcp is public and reachablegithub.com/multiagentcoordinationprotocol/macp-mcp ↗통과
- 패키지가 이 저장소를 소스로 명시검사되지 않음
- 빌드 출처(Sigstore 증명)검사되지 않음
- 오픈 소스 라이선스 (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗통과
- 최근 1년 내 커밋 또는 릴리스Last commit or release 2026-11-08github.com/multiagentcoordinationprotocol/macp-mcp ↗통과
- OpenSSF Scorecard검사되지 않음
- 패키지 이름이 인기 패키지와 유사하지 않음검사되지 않음
- 패키지 및 해당 종속성에 중요한 보안 권고 없음검사되지 않음
- 모델에 대한 숨겨진 지침 없음8 tool descriptions and the README read; no override phrases, credential paths or hidden characters통과
- 파괴적인 도구에 라벨 표시됨No tool named like delete, drop or exec통과
- 원격 엔드포인트가 MCP 핸드셰이크에 응답검사되지 않음
README
GitHub에서 보기macp-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 질문
macp MCP는 어떤 도구를 제공하나요?
8개 도구를 제공합니다. 예: start_session, propose, vote, get_commitment, verify.
MACP가 MCP 도구 사용에 어떤 역할을 하나요?
MCP가 모델이 호출할 수 있는 도구를 결정한다면, MACP는 누가 언제 도구를 사용할 수 있는지 결정하고 그 결정을 기록합니다.
특정 도구 호출을 제한하는 데 사용할 수 있나요?
네, 'macp-mcp gate' 프록시를 사용하여 정책 파일에 정의된 특정 도구에 대해 MACP 세션 승인을 요구하도록 설정할 수 있습니다.
의사결정 결과를 어떻게 검증하나요?
verify 도구를 사용하여 런타임의 기록된 이력이나 제공된 페이로드 바이트로부터 commitment hash를 다시 계산할 수 있습니다.
서버가 상태를 유지(stateful)하나요?
아니요, 모든 읽기 작업이 런타임으로부터 세션을 다시 재생하므로 서버는 stateless입니다.