Ennodia
OfficialEnnodia is a local MCP server that hands parts of a task from your current agent to other local AI agents ("harnesses") and brings their answers back.
Discover harnesses (
ennodia_list_harnesses) — find installed agents, their availability, versions, capabilities, andinputGuidancefor audio/image/video work.Discover skills (
ennodia_list_skills) — list prompt-only skills from project, user, and built-in directories without loading full instructions.Run orchestrated tasks (
ennodia_run) — the default entrypoint: plans routing to one or many local agents,auto/single/parallelmodes, optional harness/model override, per-task timeout, cwd isolation, budgets, skill requests, Codex sandbox/reasoning controls, and Judge + Result Advisor comparison.Use pragmatic mode — evidence-focused
investigate(cited findings) orpatch(unified diff proposal) recipes with explicit acceptance criteria.Continue prior work — resume the latest settled persistent task, or opt in to persistent Codex sessions.
Track and control runs (
ennodia_get_run,ennodia_cancel_run) — poll with waits, inspect status/timing/answers/events, and cancel a run plus its child tasks, Judge, or Advisor.Review past runs (
ennodia_history) — read locally persisted receipts with final answers and Judge disagreement analysis after a restart.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Ennodia review my pull request #42 with Codex and Claude, then compare the results"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Ennodia isn't another agent. It connects the agents you use.
Stay in Codex, Claude Code, or any agent you like. When a task needs another model, your agent hands that part over through Ennodia and brings the answer back. Ennodia runs on your computer, and each agent uses your own account.
Have Gemini listen to meeting.mp3 through Ennodia and tell me what was decided.Why use it
Keep the app you like. Ennodia has no window of its own. You work in your agent as before, and it can now reach the others.
Your agents work together. Any agent can hand part of a task to any other and get the answer back in your chat.
Nothing to pay, nothing to join. Ennodia is free and open source, with no account. It uses the agents and plans you have.
It grows with your agents. It is a set of tools, not a framework or a method. Each new model one agent gains becomes an ability for all of them.
It stays on your computer. Every handoff leaves a receipt there: who did the work, how long it took, and what came back.
Less to keep up with. You don't need to follow every new model. Name the task, and your agent hands it to one that can do it.
Next on the roadmap: Ennodia reads its receipts, so your agent stops repeating what failed.
Related MCP server: agentloop
What each agent adds
No model leads every task, so each agent you connect brings an ability the others lack.
Listen. Gemini hears audio files. Codex hands it the file path and gets back what Gemini heard.
Draw. Codex draws with GPT Image. Claude Code can hand it a brief and get the images back.
Review. Two other agents review the same patch in fresh sessions. Compare maps where they agree and differ.
Read. Kimi K3 in OpenCode reads long documents. Your agent hands it a spec and gets back the rules, each with its line number.
When your own agent has the ability, it does the task itself, with no handoff. See each route and the public scores behind each strength.
Install
Send this address to your agent:
try-ennodia.cherninlab.comFor manual setup, add this Model Context Protocol (MCP) server to your client:
{
"mcpServers": {
"ennodia": {
"command": "npx",
"args": ["-y", "ennodia"]
}
}
}Ennodia loads eight core tools by default: about 13,000 characters of tool definitions in each session.
Add "--tools", "all" to args for the full tool set.
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
How a handoff works
Your agent calls
ennodia_runwith the task, the agent or model to use, and a time limit.Ennodia checks the selected route, then starts that agent's own command-line tool in a fresh session, with its own tools and your account for it.
The answer comes back to your conversation, with its status and a receipt saved on your computer.
Your conversation history stays in your agent.
For two or more answers, Compare maps agreements, contradictions, and gaps.
When one answer is complete as it stands, Compare can choose it, and ennodia_run returns it unchanged.
Include relevant constraints and prior decisions in your task prompt under Keep in mind. Ennodia asks workers and Compare to return useful reminders with reasons and evidence. Your agent verifies them before carrying them into the next task. See how to read these notes.
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 reports native login checks and confirmed recovery actions. The requested task verifies model access without a separate model call first. 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
Evidence
Can Gemini hear this file?: a Codex conversation hands an audio file to Gemini through Antigravity.
Measurement plan: how Ennodia compares single agents with teams on public benchmarks.
Audio routing pilot: Codex got 10 of 10 speech questions right through Gemini, and 4 of 10 alone. Across all 30 clips the gain was not significant, and each answer took about twice as long.
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.
Each handoff costs time and uses your agents' own quotas and charges. General time or token savings have not been established. Ennodia can limit child tasks and estimated input tokens. Those estimates exclude internal harness work and are not provider bills.
Data governance · Budgets · Roadmap
Technical reference and contribution
The main entry point is ennodia_run.
The full tool set adds raw tasks, separate Compare calls, budget estimates, and the Plan Advisor, which proposes explicit tasks before execution.
MCP tools · Experimental Ennodia IO · Contributing · MIT license
bun install
bun run verifyExperimental Pragmatic mode
Pragmatic mode runs independent model attempts, tailored plans, and skill trials, then compares the evidence. It keeps bulky evidence outside the main conversation and returns findings for your agent to verify. Savings are not yet validated.
Login recovery and updates
Ennodia checks selected workers, Judge, and Advisor routes before execution. Blocked routes return a native recovery action before reviewers start. Ennodia says nothing about its own status unless an agent you asked for is blocked. Rechecks and blocked starts return compact diagnostics. The full setup panel appears only for an explicit setup request.
Your agent calls ennodia_setup to show each agent's status and fix in your current session.
Hosts that render MCP Apps, such as Claude Desktop and Visual Studio Code, can show it as a card with check buttons.
Other hosts, such as Codex and Claude Code, show the Markdown panel.
Run that action in an interactive terminal, then call ennodia_check_harnesses with the same harness and model and refresh: true, verify: true.
Run receipts keep missing reviewer coverage visible, including in compact responses.
Supported harness upgrades run once per day on use while Ennodia has no active tasks.
Set ENNODIA_AUTO_UPDATE=false to disable them.
Use ennodia_check_harnesses with upgrade: true to update and recheck immediately.
Ennodia also checks its own installation automatically. Run results report the loaded code location, version, runtime, and installation scope. The report checks required files, bundled skills, and storage access. The recheck tool refreshes this report. MCP startup instructions carry only installation problems.
Mention installation limitations when they affect the request. Cache installs can change on a future unpinned launch. These local checks do not verify the latest registry version or provider access. See recovery and updates.
Available Tools
6 toolsennodia_cancel_runCancel Ennodia runAIdempotent
Cancel a high-level run and any active child task, Judge, or Result Advisor.
Inputs: runId (required).
ennodia_get_runGet Ennodia runARead-only
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.
Inputs: runId (required), waitMs, compact, maxEvents, +2 more.
ennodia_historyList durable Ennodia run historyARead-only
Read terminal run receipts persisted under the local Ennodia history directory. Use after a restart to inspect previous final answers and Judge disagreement analysis.
Inputs: limit.
ennodia_list_harnessesList Ennodia harnessesARead-only
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.
Inputs: refresh.
ennodia_list_skillsList Ennodia skillsARead-only
Discover prompt-only skills from project, user, and built-in skill directories without returning full instruction text.
Inputs: cwd.
ennodia_runRun EnnodiaA
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 ennodia_get_run with waitMs: 30000 and includeEvents: false until terminal, then consume and verify its answer. A wait timeout does not cancel or finish the run.
Inputs: prompt (required), cwd, mode, model, +21 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a distinct lifecycle role: list_harnesses/list_skills are discovery, run starts work, get_run reads status, history reads past receipts, cancel_run stops work. The only mild overlap is get_run vs history (live vs persisted) and run vs list_harnesses routing guidance, but descriptions clarify these boundaries.
All tools use the ennodia_ prefix with snake_case verb_noun naming, which is highly consistent. Minor deviation: ennodia_run is a bare verb with no noun, while others include an object (enumodia_list_harnesses, ennodia_get_run).
Six tools is well-scoped for an orchestration server, covering discovery, execution, polling, history, and cancellation without redundancy. Each tool earns its place in the run lifecycle.
The lifecycle is well covered: discover harnesses/skills, start run, poll, cancel, and read history. Minor gap: no explicit tool for listing or retrieving an in-progress run's result beyond polling, but get_run with waitMs handles terminal results adequately.
Maintenance
Related MCP Connectors
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server for mandates, delegation, policy-gated execution, credential grants, and audit.
MCP Server for an Agent Task Marketplace
Related MCP Servers
- AlicenseAqualityDmaintenanceMCP server orchestrating local CLI agents (Claude Code, OpenAI Codex, Google Gemini) for cross-validation, second opinions, and persona-driven prompting.18MIT
- AlicenseNot gradedqualityCmaintenanceMCP server that enables AI agents to run a deterministic orchestration loop with decomposition, subagent execution, and review feedback across multiple LLM backends.61MIT
- FlicenseNot gradedqualityDmaintenanceMulti-model agent orchestration MCP server that enables plan-code-review-deliver pipelines with configurable providers and models.-
- AlicenseNot gradedqualityBmaintenanceMCP server for agentic task orchestration and management, enabling AI agents to create goals, plan tasks with acceptance criteria, track dependencies, request human input, and provide proof of completion.16 npm3MIT