hermes-mcp

Hermes MCP

Hermes MCP is a FastAPI + MCP supervisor for market interpretation, strategy selection, and Trader control.

What Hermes does

• builds a market narrative from regime data
• scores strategy fit for each account/market concern
• records decision snapshots for audit and dashboarding
• optionally dispatches Trader control actions through a single guarded write path

Surface

• MCP transport: /mcp/sse
• Health: /health
• Dashboard: /dashboard/
• Primary tool: report()

The dashboard now includes:

• overview
• playbooks
• concern detail pages
• decision changes

The report() tool returns the current Hermes state plus a compact per-concern summary including:

• concern id
• active playbook
• active assigned strategies
• balances
• total value

Hermes to Trader control path

Hermes reads Trader state via strategy snapshots and writes only through Trader's canonical action tool:

• apply_control_decision(payload)

Dispatch is gated locally by:

• HERMES_ALLOW_ACTIONS

When the gate is false, Hermes still makes and records decisions, but returns a blocked dispatch result instead of changing Trader state.

Run

./run.sh 8590

Test

./tests.sh

Replay decisions

Hermes now stores a full replay_input bundle with each new decision, so stored decisions can be replayed against the current decision engine.

Replay recent decisions:

python3 scripts/replay_decisions.py --limit 20

Only show changed outcomes:

python3 scripts/replay_decisions.py --limit 50 --only-changed

JSON output:

python3 scripts/replay_decisions.py --limit 50 --json

Optional filter by concern:

python3 scripts/replay_decisions.py --concern-id <concern-id>

Note: decisions created before this replay capture existed will not have replay_input yet.