Mmcp.market

Ennodia MCP server

by cherninlab·io.github.cherninlab/ennodia·v0.3.0
No reviews yet

Try other agents, models, and skills from your familiar AI workflow through a local MCP server

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

5 stars327 downloads/wk

Reviews

Write one

Nobody has reviewed Ennodia yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Ennodia tools (26, 6 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • ennodia_cancel_comparewrite action

    Cancel a running Judge + Result Advisor comparison and its active child task.

  • ennodia_cancel_plan_advicewrite action

    Cancel a running Plan Advisor request and its Advisor task.

  • ennodia_cancel_runwrite action

    Cancel a high-level run and any active child task, Judge, or Result Advisor.

  • ennodia_cancel_taskwrite action

    Cancel a running task by task ID.

  • ennodia_estimate_budget

    Estimate the input-token budget for a planned Ennodia run and report whether optional limits would be exceeded before starting child tasks.

  • ennodia_estimate_compositional_budget

    Resolve focused compositional slices to harnesses and estimate child-task and later Judge + Result Advisor budget without starting child processes.

  • ennodia_get_compare

    Inspect comparison status, candidate inputs, Judge analysis, Result Advisor answer, child task IDs, degradation state, and ETA.

  • ennodia_get_compositional_status

    Inspect a batch of compositional shard tasks, group running and terminal states, and return successful task IDs ready for Judge + Result Advisor comparison.

  • ennodia_get_plan_advice

    Inspect Plan Advisor status, validation issues, frozen inventory identity, proposal, validated plan, digest, budgets, events, and ETA. A plan can be launched only when status is ready. An authorized plan has status consumed and cannot run again.

  • ennodia_get_runwrite action

    Inspect a run or wait up to waitMs for completion. Prefer waitMs: 30000, compact: true and includeEvents: false while awaiting results. A nonterminal response means work continues; do not claim its findings were consumed.

  • ennodia_get_task

    Inspect task status, captured output, events, and ETA.

  • ennodia_history

    Read terminal run receipts persisted under the local Ennodia history directory. Use after a restart to inspect previous final answers and Judge disagreement analysis.

  • ennodia_install_skills

    Install bundled Ennodia Agent Skills into native harness skill directories. Defaults to dryRun so clients can inspect planned writes before applying them.

  • ennodia_list_compares

    List Judge + Result Advisor comparisons started by this Ennodia MCP server process.

  • ennodia_list_harnesses

    Discover local harnesses, availability, versions, capabilities, adapter notes, and inputGuidance. Before audio/image/video work, read inputGuidance: model capabilities do not guarantee native input through a harness. Use first when setup or routing fails.

  • ennodia_list_plan_advice

    List recent Plan Advisor requests started by this Ennodia MCP server process.

  • ennodia_list_runs

    List high-level Ennodia runs started by this MCP server process.

  • ennodia_list_skills

    Discover prompt-only skills from project, user, and built-in skill directories without returning full instruction text.

  • ennodia_list_tasks

    List tasks started by this Ennodia MCP server process.

  • ennodia_plan

    Classify a prompt and preview the route Ennodia would take without starting any child process. Use before ennodia_run when you want to inspect routing.

  • ennodia_runwrite action

    Start a high-level Ennodia orchestration. Set pragmatic for evidence-focused investigation or patch proposals with one or more independent workers. Use Plan Advisor for tailored model and skill assignments. Use this as the default entrypoint: it plans routing, starts one or more local harness tasks, optionally compares successful outputs, and returns a run ID. Runs usually take minutes; use ennodi

  • ennodia_start

    Start raw child harness tasks without a run-level Judge + Result Advisor pass. Use for debugging, direct harness calls, or manual comparison workflows; prefer ennodia_run for normal end-to-end use.

  • ennodia_start_advised_plan

    Explicitly launch the exact validated worker plan from a ready Plan Advisor request. Ennodia re-checks the caller-supplied digest, current harness and skill inventory, caller allowlisted model assignments, and budget before starting the first worker task; any mismatch fails closed with zero launches. A plan is single-use after authorization. Provider model availability remains unverified until the

  • ennodia_start_compare

    Compare completed Ennodia task outputs or caller-supplied responses. The Judge maps agreements, contradictions, and risks; the Result Advisor then combines that analysis into the final answer. Returns a Compare ID to inspect with ennodia_get_compare.

  • ennodia_start_compositional

    Start one focused child task per slice for compositional reviews. Poll the returned task IDs, then pass useful completed task IDs to ennodia_start_compare for a Judge + Result Advisor comparison.

  • ennodia_start_plan_advice

    Ask one Advisor to propose a bounded team of harness, model, and skill assignments. This starts only the Advisor task: its output is strict, inert plan data that Ennodia validates and never executes automatically. Poll ennodia_get_plan_advice, then explicitly call ennodia_start_advised_plan with the returned digest.

Public scan report

scanner v0.1.5 · 2026-09-19 · same rubric, same numbers if you re-run it

no findings
  • Code scan22 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 1 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the Ennodia repository's README, as published. We do not edit it. Read it on GitHub

Keep your agent. Get another way forward.

When a task stalls, Ennodia lets your primary artificial intelligence (AI) agent try another agent, model, or skill. The findings come back to the same conversation. You keep your familiar interface and decide what to try next.

Use Ennodia MCP to get a second opinion on this bug.
Give one available agent the failing test and our attempted fixes.
Request a different explanation and a way to test it.
Bring the findings back here.

When it helps

  • A task is stuck and you want to check another approach.
  • A skill looks useful, but you want to try it in a separate task first.
  • Two answers disagree and you need to identify the next check.
  • An unsuccessful attempt can help you avoid repeating the same approach under the same conditions.

Your main agent checks the findings and integrates useful work. Additional attempts consume time and resources. General time or token savings have not been established.

Install

Send this address to your primary agent:

try-ennodia.cherninlab.com

For manual setup, add this Model Context Protocol (MCP) server to your client:

{
  "mcpServers": {
    "ennodia": {
      "command": "npx",
      "args": ["-y", "ennodia"]
    }
  }
}

Requirements: Bun 1.3.14 or newer, a compatible MCP client, and a supported agent with working provider access. npx downloads Ennodia. Bun runs it. You can also use bunx ennodia.

Get your first result · Installation for agents

Use your installed agents and skills

Supported agents: Codex CLI, Claude Code, OpenCode, Kilo Code, Kiro CLI, Cline, Hermes Agent, and Antigravity. Model availability and tool permissions depend on the installed agent and its provider configuration. Discovery finds executable commands. It does not verify authentication or model access. Codex workers use a read-only sandbox by default.

Ennodia discovers native Agent Skills and can request them for specific tasks. A separate task keeps the trial outside the main conversation. Native agents can also select unrequested skills from their own environment.

Recipes · Using skills · Understand results

See it in practice

  • Building Ennodia with Ennodia: a worker patch, a failed login, and primary-agent corrections.
  • Find stale documentation: a small review with known answers.
  • Try a skill separately: two attempts against the same contract.

The existing saved-answer benchmark is a regression check, not a live speed or cost comparison. Measurement plan

Data and limits

Ennodia runs locally without an Ennodia-hosted service. Selected agents can send material to their configured model providers. Terminal run history is stored locally and can be disabled with ENNODIA_HISTORY=0.

Ennodia can limit child tasks and estimated input tokens. Those estimates exclude internal harness work and are not provider bills. Automatic agent updates and recommendations learned from past results remain future work.

Data governance · Budgets · Roadmap

Technical reference and contribution

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

Runs npx -y ennodia on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add ennodia -- npx -y ennodia
Add to Cursor

Ennodia: common questions

Is Ennodia MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Ennodia safety report
How do I install Ennodia?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Ennodia need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Ennodia maintained?
The last commit was 2 days ago (2026-09-18). The latest release is v0.3.0.

More from cherninlab →