MCP 服务器

Ennodia

MCP server that orchestrates multi-agent reviews by running installed agent CLIs, tracking child tasks, and using Compare to produce a traceable recommended answer with receipts.

README

<p><strong>Model Context Protocol (MCP) server for multi-agent review with Compare and traceable receipts</strong></p>

</div>

Ennodia gives your primary agent access to installed agent command-line interfaces (CLIs). It tracks each child task and uses model-led Compare to show agreements, disagreements, omissions, and one recommended answer with receipts.

Before work, an optional Plan Advisor can propose a bounded set of harnesses, models, and skills. It does not start the proposed work.

Install

Send this address to your primary agent. The agent can then complete the installation:

try-ennodia.cherninlab.com

To run Ennodia directly as a standard input/output (stdio) MCP server, use:

npx -y ennodia

To use Bun directly, run bunx ennodia.

For a registry or client installer, use the Ennodia Smithery page.

For manual installation or local development, see Quickstart.

What Ennodia does

Discovers available local artificial intelligence (AI) tools
Plans a route with a caller-provided category or keyword fallback
Estimates preflight input tokens and enforces local caps on that estimate
Starts and monitors child tasks
Shows status, elapsed time, logs, and failures
Cancels tasks and runs explicitly
Lets a Plan Advisor propose an inert, validated work plan
Compares multiple completed outputs with a Judge
Lets a Result Advisor combine the Judge findings into one answer

ennodia_run is the main entrypoint. It plans and starts tasks. It can also use Compare. It returns a run identifier (ID) for use with ennodia_get_run.

See MCP tools for the full tool and parameter reference.

Use Ennodia for work that needs additional model analysis. A run usually takes minutes. Compare adds two serial model passes after the child agents finish.

Judge, Plan Advisor, and Result Advisor

Each role has limited responsibilities:

Plan Advisor runs before work when requested. It proposes explicit harness, model, and skill assignments as inert data. Ennodia validates the proposal against a frozen inventory. Plan Advisor cannot execute it. The caller must use a separate call to start the validated plan once.
Judge runs during Compare and maps agreements, contradictions, unique evidence, omissions, and risks across completed outputs.
Result Advisor follows the Judge. It uses the Judge findings and original outputs to recommend an answer. If Judge analysis is not usable, it uses basis: "candidates-only". This status makes the degradation visible.

Ennodia IO

The separate @cherninlab/ennodia-io package provides a local Hypertext Transfer Protocol (HTTP) and TypeScript interface. Apps can use it with user-supplied keys and installed local agents:

npx -y @cherninlab/ennodia-io

See Ennodia IO for supported fields, authentication behavior, cross-origin resource sharing rules, and current limits.

Supported harnesses

Codex CLI
Claude Code
OpenCode
Kilo Code
Kiro CLI
Cline CLI
Hermes Agent
Antigravity

Adapters stay thin. Core modules contain shared routing, trace data, task state, recovery, and Compare logic.

Evaluated candidates include Gemini CLI, GitHub Copilot CLI, Amp, Aider, Goose, Qwen Code, and Cursor CLI. Ennodia does not include these candidates.

Ennodia can add a candidate after verification of a supported prompt-in and text-out interface. Verification must not use permission-bypass flags or provider-private APIs.

Documentation

Installation for Agents: agent-controlled installation
Quickstart: manual installation and local development
MCP Tools: full tool parameter reference
How Ennodia Works: orchestration pipeline
Second Opinions: replicate, decompose, and red-team patterns
Data Governance: local storage and data movement boundaries
Controlled English: ASD-STE100 rules and Ennodia technical terms
Comparisons: comparisons with adjacent tools
Benchmarks: deterministic bug-recall results
Better Audits: prompt rubrics for Compare

Benchmarks

The current benchmark is multi-model-bug-recall. It uses small TypeScript review fixtures and committed bug oracles. Run the deterministic suite with:

bun run bench:bug-recall

Live harness runs are available through bun run bench:bug-recall:live and are kept out of bun run verify.

The current dated fixture snapshot is published in Benchmarks: 4 cases, with ennodia-parallel-compare at 100% recall and 100% precision.

Contribute

Ennodia is under active development. You can submit bug reports and small, focused pull requests. See CONTRIBUTING.md for the local verification workflow.