base76-research-lab avatar

Conductor Graph Mcp

base76-research-lab/conductor-graph-mcp

Snapshots your entire CognOS agent system in one tool call. You get a JSON graph showing all 12+ nodes (trustplane-gateway, token-compressor, session-memory, armada-bus, plus agent-critic, agent-curator, agent-ethics, etc.) with live status checks pulled from HTTP endpoints, log files, SQLite traces, and process monitors. The get_agent_graph tool returns nodes, edges, and system summary. Use get_blocked_nodes when something breaks, get_node_status for drilling into specific components, or get_edges to map communication flow. Built for the FNC architecture where Claude acts as conductor over a distributed agent fleet. You point it at your local CognOS instance via COGNOS_BASE_URL and it reads the whole topology instantly.

tools
4
auth
Secret needed
transport
STDIO
env vars
2
last updated
Mar 3, 2026

Tools

4 tools

Public tool metadata for what this MCP can expose to an agent.

get_agent_graphFull graph — nodes + edges + summary

Full graph — nodes + edges + summary

No parameter schema in public metadata yet.

get_node_statusLive status for a specific node

Live status for a specific node

No parameter schema in public metadata yet.

get_edgesOnly edges (communication flow)

Only edges (communication flow)

No parameter schema in public metadata yet.

get_blocked_nodesShortcut: what is broken right now?

Shortcut: what is broken right now?

No parameter schema in public metadata yet.

Sponsors

Configuration

COGNOS_BASE_URL

URL of the TrustPlane/CognOS gateway (default: http://127.0.0.1:8788)

COGNOS_API_KEYsecret

API key for the CognOS gateway (optional, leave empty if not required)

Readme

Conductor Graph MCP Server

mcp-name: io.github.base76-research-lab/conductor-graph-mcp

Conductor-Graph-MCP

An MCP server that exposes a CognOS agent system as a machine-readable JSON graph. The conductor (Claude) calls a single tool and gets an immediate full system snapshot.

Built on the FNC architecture: Field (agents) → Node (processing) → Cockpit (oversight)


Installation

# From PyPI (recommended)
pip install conductor-graph-mcp

# Or from source
git clone https://github.com/base76-research-lab/conductor-graph-mcp
cd conductor-graph-mcp
pip install -e .

Usage with Claude Code

Add to ~/.claude/settings.json under mcpServers:

{
  "mcpServers": {
    "cognos-graph": {
      "command": "python3",
      "args": ["-m", "conductor_graph_mcp"],
      "env": {
        "COGNOS_BASE_URL": "http://127.0.0.1:8788",
        "COGNOS_API_KEY": "your-key"
      }
    }
  }
}

Or with uvx:


View the full README on GitHub

Details

Repository
github.com/base76-research-lab/conductor-graph-mcp
Category
AI & LLM Tools
Package
conductor-graph-mcp
Transport
STDIO
Auth
Required
Registry
MCP registry, active

More from base76-research-lab

Related AI & LLM Tools MCP servers

View all
1bch1212 avatarMcp Grantiqbch1212/mcp-grantiqSearch US grants + federal contracts (Grants.gov + SAM.gov) from any LLM.0stars
2bleedmode avatarDear Userbleedmode/dearuserTells you how you and your Claude agent actually work together. Local-only, no API keys.0stars
3bobbyrgoldsmith avatarQuarterbackbobbyrgoldsmith/quarterbackStrategic task prioritization and agent orchestration for multi-project operators0stars
4bystray avatarGonka Second Opinion (multi-model)bystray/gonka-mcp-serverA second opinion for AI agents: one prompt across several live Gonka models + roles, one call.0stars
5capitalthought avatarDoomcapitalthought/doomObsolescence-risk screening: predicts if a product gets absorbed into core LLM-platform features.0stars
6christopherdavenport avatargithub-twinchristopherdavenport/github-twinPersonal RAG over your GitHub history (commits, code, reviews), served to Claude Code over MCP.0stars