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.
mcp-name: io.github.base76-research-lab/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)
# 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 .
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:
{
"mcpServers": {
"cognos-graph": {
"command": "uvx",
"args": ["conductor-graph-mcp"],
"env": {
"COGNOS_BASE_URL": "http://127.0.0.1:8788",
"COGNOS_API_KEY": "your-key"
}
}
}
}
Restart Claude Code — the server activates automatically.
Note: Requires MCP SDK ≥ 1.0 (
mcpon PyPI).
| Tool | Description |
|---|---|
get_agent_graph | Full graph — nodes + edges + summary |
get_node_status(node_id) | Live status for a specific node |
get_edges | Only edges (communication flow) |
get_blocked_nodes | Shortcut: what is broken right now? |
conductor
trustplane-gateway
token-compressor
session-memory
armada-bus
agent-critic
agent-curator
agent-ethics
agent-synth
agent-self
agent-srt
agent-indexer
get_agent_graph() # Full system overview
get_node_status("trustplane-gateway") # One specific node
get_blocked_nodes() # What is broken?
get_edges() # Communication flow
| Node | Source |
|---|---|
trustplane-gateway | HTTP GET /healthz + /v1/providers/health |
token-compressor | /tmp/b76_compress.log |
session-memory | /tmp/b76_save.log + SQLite traces.sqlite3 |
armada-bus | /tmp/b76_armada_bus.json + /tmp/b76_armada_bus.log |
agent-* | psutil — is the process running? |
conductor | Always active (the conductor itself) |
| Variable | Default | Description |
|---|---|---|
COGNOS_BASE_URL | http://127.0.0.1:8788 | TrustPlane gateway URL |
COGNOS_API_KEY | (empty) | API key for gateway auth |
# Test that the server starts
python3 -m conductor_graph_mcp
# Stop the gateway → trustplane-gateway.status = "error"
# get_blocked_nodes() should return trustplane-gateway
# Run a /save → session-memory.metrics.entries increases
# get_node_status("session-memory") shows new count
MIT — Base76 Research Lab
COGNOS_BASE_URLURL of the TrustPlane/CognOS gateway (default: http://127.0.0.1:8788)
COGNOS_API_KEYsecretAPI key for the CognOS gateway (optional, leave empty if not required)
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent