MCP server Multi-Agent Coordination Protocol
Коммит 8 нояб. 2026 г.Позволяет MCP clients запускать или участвовать в управляемых сессиях принятия решений с проверяемыми обязательствами и кворумным ограничением вызова инструментов.
Также известен как multiagentcoordinationprotocol/macp-mcp-typescript
- Звёзды
- 0
- Инструменты
- 15
- Загрузки, 30 дней
- —
- Последняя версия
- —
- Последний коммит
- 8 нояб. 2026 г.
- Лицензия
- Apache-2.0
Что такое Multi-Agent Coordination Protocol MCP?
Позволяет MCP clients запускать или участвовать в управляемых сессиях принятия решений с проверяемыми обязательствами и кворумным ограничением вызова инструментов. Он предоставляет 15 инструментов, например start_session, propose, evaluate.
Сводка сгенерирована из README проекта
О Multi-Agent Coordination Protocol MCP server
Разработчики, использующие Claude Desktop, Claude Code или Cursor, могут координировать решения нескольких агентов через этот сервер. Он позволяет AI модели инициировать или участвовать в управляемых сессиях принятия решений, где действия требуют проверяемых обязательств и одобрения на основе кворума. Подключаясь к среде выполнения MACP через gRPC, сервер позволяет агентам предлагать варианты, оценивать предложения и голосовать для достижения консенсуса.
Эта реализация на TypeScript предоставляет инструментарий для управления всем жизненным циклом сессии: от использования start_session до финализации результатов с помощью команды commit. Она предназначена для работы совместно со средой выполнения MACP, которую можно запустить локально с помощью Docker. Для рабочих сред сервер поддерживает аутентификацию через bearer token. Помимо стандартных сессий, он включает режим gating, который выступает в роли прокси для вышестоящих MCP servers, гарантируя, что определенные вызовы инструментов будут выполнены только после достижения необходимого порога одобрений.
Что вы можете с ним делать
- 1Координация планов развертывания нескольких агентовAI агент может начать формальную сессию принятия решений с другими участниками, чтобы согласовать конкретную стратегию canary-релиза.
- 2Обеспечение кворума для чувствительных инструментовВы можете обернуть существующий сервер файловой системы с помощью gate, чтобы требовать нескольких одобрений перед выполнением любых операций записи файлов.
- 3Проверка целостности решенийРазработчики могут пересчитывать хеши, чтобы убедиться, что записанное обязательство соответствует фактическому результату сессии.
Взято из README проекта. Каждый вариант использования проверен на соответствие цитате из него.
Инструменты Multi-Agent Coordination Protocol MCP 15
Определено из READMEstart_sessionproposeevaluatevotecommitget_sessionget_commitmentverifyservertoolmodeparticipants
| start_session | — | |
| propose | — | |
| evaluate | — | |
| vote | — | |
| commit | — | |
| get_session | — | |
| get_commitment | — | |
| verify | — | |
| server | — | |
| tool | — | |
| mode | — | |
| participants | — |
Показать все 15 инструментовПоказать меньше инструментов
thresholdttl_mspolicy_version
| threshold | — | |
| ttl_ms | — | |
| policy_version | — |
Конфигурация
MACP_AGENT_IDMACP_ALLOW_INSECUREMACP_AUTH_TOKENMACP_RUNTIME_TARGET
| Название | Описание | Тип |
|---|---|---|
| MACP_AGENT_ID | — | |
| MACP_ALLOW_INSECURE | — | |
| MACP_AUTH_TOKEN | — | |
| MACP_RUNTIME_TARGET | — |
Автоматические проверки
Запущено 14 нояб. 2026 г.Полный отчёт →Еще не проверено. Для сервера требуется оценка 80, отсутствие серьезных проблем и достаточно данных для нашей проверки. Как работают проверки · Что исправить, чтобы получить больше баллов
- Связанный и доступный исходный репозиторийmultiagentcoordinationprotocol/macp-mcp-typescript is public and reachablegithub.com/multiagentcoordinationprotocol/macp-mcp-typescrip ↗Пройдено
- Пакет указывает этот репозиторий как источникНе проверялось
- Происхождение сборки (аттестация Sigstore)Не проверялось
- Open source лицензия (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Пройдено
- Коммит или релиз за последний годLast commit or release 2026-11-08github.com/multiagentcoordinationprotocol/macp-mcp-typescrip ↗Пройдено
- OpenSSF ScorecardНе проверялось
- Имя пакета не похоже на популярный пакетНе проверялось
- Нет критических предупреждений в пакете или его зависимостяхНе проверялось
- Нет скрытых инструкций для модели15 tool descriptions and the README read; no override phrases, credential paths or hidden charactersПройдено
- Деструктивные инструменты помеченыNo tool named like delete, drop or execПройдено
- Удалённая конечная точка отвечает на рукопожатие MCPНе проверялось
README
Открыть на GitHub@multiagentcoordinationprotocol/mcp
An MCP server that lets any MCP client (Claude Desktop, Claude Code, Cursor and
others) run or join a MACP Decision
session. It is the TypeScript twin of the Python
macp-mcp. Both
expose the same tool surface: the same names, input schemas and outputs,
pinned by one shared manifest (Tool contract).
Package versions are independent of the Python macp-mcp; tool parity is
enforced by make verify-contract, not by matching version numbers.
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.
MCP client (model) ──stdio──▶ macp-mcp ──gRPC──▶ MACP runtime
tool calls one MACP agent enforces membership, order,
(macp-sdk-typescript) identity; records the Commitment
Install
npx -y @multiagentcoordinationprotocol/mcp # or: npm i -g @multiagentcoordinationprotocol/mcp
Node 20 or newer. The installed binary is called macp-mcp, like the Python
server's. 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. For several agents to 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": "npx",
"args": ["-y", "@multiagentcoordinationprotocol/mcp"],
"env": {
"MACP_RUNTIME_TARGET": "127.0.0.1:50051",
"MACP_AGENT_ID": "coordinator",
"MACP_ALLOW_INSECURE": "1"
}
}
}
}
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 \
-- npx -y @multiagentcoordinationprotocol/mcp
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
These are the same variables, with the same defaults, as the Python server.
| 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/true/yes/on 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. |
evaluate |
write | Record a scored assessment (APPROVE / REVIEW / BLOCK / REJECT, confidence 0..1) before voting. |
vote |
write | Cast this agent's APPROVE / REJECT / ABSTAIN vote on a proposal. |
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. |
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. |
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 upstream tool calls (macp-mcp gate)
macp-mcp gate is a second mode of the same binary. It runs as an MCP server
in front of another (upstream) MCP server, and puts the tool calls you name
behind a MACP session: a matching call reaches the upstream only after a
Quorum or Decision session commits approve. Every other call passes straight
through.
macp-mcp gate --policy gate.json --upstream npx -y @modelcontextprotocol/server-filesystem /srv/data
--upstream takes the rest of the command line as the upstream's stdio
command. The gate uses the same environment variables as the base server
(MACP_AGENT_ID is the gate's identity: it initiates and commits every
session). The upstream inherits the gate's environment minus
MACP_AUTH_TOKEN, so the gate's credential never reaches it.
gate.json names the rules; the first rule whose tool matches wins (exact
name, or a glob with * and ?):
{
"version": 1,
"server": "filesystem",
"rules": [
{ "tool": "write_*", "mode": "macp.mode.quorum.v1", "participants": ["alice", "bob", "carol"], "threshold": 2 },
{ "tool": "move_file", "mode": "macp.mode.decision.v1", "participants": ["alice", "bob"], "ttl_ms": 60000 }
]
}
| Field | Meaning |
|---|---|
server |
The upstream's name, bound into every gated call's context_id. |
tool |
Exact tool name or glob. |
mode |
macp.mode.quorum.v1 (ApprovalRequest + ballots) or macp.mode.decision.v1 (Proposal + votes). |
participants |
The approvers. Must not include the gate's own agent id. |
threshold |
APPROVE ballots needed, in either mode. Default: a strict majority of participants. |
ttl_ms |
Session TTL. Default 300000. |
policy_version |
Optional RFC-MACP-0012 policy to bind the session to, for example one of the spec's policy packs. |
For a gated call the gate:
-
Starts a session whose
context_idissha256:+ the hex SHA-256 of the RFC 8785 (JCS) form of{"arguments", "server", "tool"}. The same canonical JSON travels in the ApprovalRequestdetails(Quorum) or the Proposalrationale(Decision), so an approver can recompute the binding. -
Commits
approveas soon as the approvers' latest ballots reach the threshold, ordenyas soon as they no longer can (REJECT and ABSTAIN both count as not-approve). -
On
approve, forwards the call and adds the commitment to the result, beside 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; the base server'sverifytool recomputes it from the runtime's history. -
Otherwise refuses with a tool error, and never calls the upstream:
POLICY_DENIED: …when the session commitsdeny(or a bound policy refuses the commitment),SESSION_NOT_OPEN: …when the session expires or is cancelled without a commitment. If the session is still open 5 s after its TTL, the gate cancels it. A call whose arguments hold an integer outside ±(2^53−1) is refused withINVALID_ARGUMENT: …before any session opens: JSON may already have rounded it, so it has no canonical form.
Approvers are ordinary MACP agents, for example a base macp-mcp server
driven by a person or another model, voting through the runtime. See
examples/gated-tool-call.md for a full
transcript. The policy schema, CLI flags, wire values and context_id test
vectors live in contract/gate/, byte-identical to the
Python macp-mcp's.
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/gate-policy.test.ts
(added in #10)
and the Python macp-mcp's
test_gate_policy.py
(#12).
Tool contract
contract/tools.json pins the tool names,
descriptions, annotations, input schemas and output schemas as fully inlined
JSON Schema 2020-12. The Python macp-mcp generates it, and this repo keeps a
byte-identical copy. This server does not derive its schemas from code: it
serves the manifest verbatim from tools/list and validates every call's
arguments against it with Ajv, so the advertised surface cannot drift from
the file. The file also ships in the npm package as
@multiagentcoordinationprotocol/mcp/contract/tools.json.
The gate's contract (contract/gate/) is vendored the same way. CI fails if
any of these files drifts from the Python repo's (make verify-contract).
After a deliberate surface change lands in macp-mcp, run make sync-contract
and implement the change here.
Library use
The package also exports the pieces, for embedding the server in another process or testing against it:
import { buildServer, loadSettings } from '@multiagentcoordinationprotocol/mcp';
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
const { server } = buildServer({ settings: loadSettings() });
await server.connect(new StdioServerTransport());
Development
npm ci
npm run check && npm run lint && npm run format:check
npm test # unit tests (fake runtime, in-memory MCP client)
make verify-contract # contract/tools.json == the Python macp-mcp's
# Acceptance: two stdio MCP clients drive a Decision session to RESOLVED
docker run -d --rm --name macp-runtime-test -p 50051:50051 \
-e MACP_BIND_ADDR=0.0.0.0:50051 -e MACP_ALLOW_INSECURE=1 -e MACP_MEMORY_ONLY=1 \
ghcr.io/multiagentcoordinationprotocol/macp-runtime:0.14.1
npx tsx scripts/wait-for-runtime.ts
npm run test:integration
Releases follow macp-sdk-typescript: release-please opens the release PR, and merging it creates the GitHub release, which publishes to npmjs with provenance.
License
Apache-2.0
Вопросы о Multi-Agent Coordination Protocol MCP
Какие инструменты предоставляет Multi-Agent Coordination Protocol MCP?
Он предоставляет 15 инструментов, включая start_session, propose, evaluate, vote, commit.
Как установить MACP MCP server?
Вы можете установить его с помощью npx или npm: 'npx -y @multiagentcoordinationprotocol/mcp' или 'npm i -g @multiagentcoordinationprotocol/mcp'.
Могу ли я использовать это для ограничения определенных вызовов инструментов?
Да, режим 'macp-mcp gate' работает как MCP server перед вышестоящим сервером, чтобы поместить конкретные вызовы инструментов под контроль сессии MACP.