Brain MCP logo

Brain MCP

Unclaimed

by DevvGwardo

Hermes Brain — Multi-agent orchestration for Hermes Agent. SQLite-backed coordination layer, MCP-compatible, zero-token coordination overhead.

Install

$pip install -e .

Set up this server

This server needs project-specific setup. Follow the project instructions; no reusable public launch command is available yet.

Project instructions

More in Databases

Browse the full directory

Unclaimed listing

Is this your MCP server?

This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.

Claim this server

Security profile

Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works

36 of 36 tools

Documented tools (36)

From project documentation. A server handshake does not verify each tool’s description or behavior.

brain_agents

Live health of all agents (status, heartbeat age, claims)

brain_auto_gate

Run gate in a loop, wait for fixes, retry until clean

brain_checkpoint

Save full working state

brain_checkpoint_restore

Recover after context compression

brain_claim

Lock a file/resource (TTL-based mutex)

brain_claims

List active locks

brain_context_get

Read the ledger

brain_context_push

Log action/discovery/decision/error

brain_context_summary

Condensed view for context recovery

brain_contract_check

Validate all contracts — catches param mismatches, missing functions

brain_contract_get

Read other agents' contracts before coding

brain_contract_set

Publish what your module provides / expects

brain_dm

Direct message another agent

brain_forget

Remove outdated memories

brain_gate

Run compile + contract check, DM errors to responsible agents

brain_inbox

Read your DMs

brain_keys

1.6ms

brain_metrics

Success rates, duration, error counts per agent

brain_plan

Create a task DAG with dependencies

brain_plan_next

Get tasks whose dependencies are satisfied

brain_plan_status

Overall progress

brain_plan_update

Mark task done/failed (auto-promotes dependents)

brain_post

Post to a channel

brain_pulse

Heartbeat with status + progress (returns pending DMs)

brain_read

Read from a channel

brain_recall

Search memories from previous sessions

brain_register

Name this session

brain_release

Unlock

brain_remember

Store persistent knowledge (survives brainclear)

brain_respawn

Replace a failed agent with recovery context

brain_sessions

List active sessions

brain_status

Show session info + room

brain_swarm

Spawn multiple agents in one call

brain_wake

Spawn a new agent (hermes, claude, or headless)

brain_workflow_apply

Persist the compiled workflow into brain state + a task DAG, optionally write conductor JSON

brain_workflow_compile

Turn one natural-language goal into phases, agents, file scopes, and conductor config

Tool change history

Compared across complete checks of the same configuration. Tools were listed, not invoked. Input-schema changes are not measured here.

No complete tool checks yet.

FAQ

Questions about Brain MCP Server

How do I connect Brain MCP Server to Claude?
The listing records `pip install -e .` as its setup step. Run it, then follow the repository's instructions for the client configuration; the listing names Claude Code as compatible clients.
Is Brain MCP Server free?
The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
What can Brain MCP Server do?
Brain MCP Server documents 36 tools to the agent, including brain_agents, brain_auto_gate, brain_checkpoint. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.