MCP.Market

Concord Engine MCP server

by harsh-chandak·io.github.harsh-chandak/concord-engine·v0.3.2
No reviews yet

Scale parallelism. Preserve alignment. A fleet of coding agents builds one task in parallel against

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

full report

Adoption
Growing

0 stars575 downloads/wk

Reviews

Write one

Nobody has reviewed Concord Engine yet.

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

Concord Engine tools (12, 3 write)

write = sends, deletes, buys or posts

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

  • bind_contractwrite action

    Put a stored contract's decisions in force at PM layer. Refuses any that contradict a decision already recorded rather than overriding it — a new contract quietly winning over a live decision is the failure this tool exists to prevent. Run this before briefing anyone.

  • binding_decisions

    The decisions currently in force. Call this BEFORE writing code so you implement what was actually decided rather than guessing. Optionally filter by subject.

  • brief_unit

    Everything one worker is told, and nothing else: its goal, the files it owns, the decisions it must honour, what it may not decide alone, and what done means. Hand `instructions` to the worker verbatim. Do not also hand it the contract — a worker that can read other units' work reasons about it.

  • cost_report

    What briefing cost against handing every worker the whole contract. Byte counts are measured; token figures are estimates from a stated chars-per-token divisor, and are labelled as such wherever they appear.

  • fleet_plan

    The units in dependency order, with each one's brief, so you can fan out a wave at a time and know what is allowed to start now. Give each worker only its own brief.

  • generate_docs

    The design doc nobody writes, rendered from the decision log — so it cannot drift from what was actually decided and enforced. Returns markdown, or writes it to a path.

  • open_conflicts

    Conflicts that are unresolved, with whose turn it is and what has already been tried. Each one is a packet you can act on without reading a transcript.

  • record_attempt

    Record a failed attempt to resolve a conflict, with what was tried and why it failed. Two attempts at a layer and it escalates to the layer above; from the PM it escalates to the human.

  • record_decision

    Record a decision as a team lead or PM. REFUSES and returns the conflict if it contradicts a decision already in force, so you find out before the work is done rather than at integration. Workers do not call this — they write code. Read-only on conflict.

  • run_acceptancewrite action

    Runs the command behind every acceptance criterion and reports which passed. The contract's own commands, not an opinion about whether the work looks finished.

  • status

    How often conflicts reached a human. The number this tool exists to drive to zero.

  • write_contractwrite action

    Validate a contract and store it. REFUSES an invalid one and returns every problem at once, with the schema, so you repair it in a single round trip instead of four. A contract that contradicts itself is caught here, before any worker has started.

Public scan report

scanner v0.1.10 · 2026-10-24 · same rubric, same numbers if you re-run it

no findings
  • Code scan25 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 0 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

How Concord Engine compares

Against every graded Productivity MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 90% of 1,299 Productivity servers
Tools
12
the typical Productivity server has 7
Tools that change things
25%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
575
more than 85% of 427 Productivity servers with a package

What its tools let an agent do: 7 read · 3 create · 1 change · 1 run or deploy

Install Concord Engine in Claude Code, Cursor or VS Code

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

claude mcp add concord-engine -- npx -y concord-engine
Add to Cursor

What the publisher says

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

Concord Engine

Scale parallelism. Preserve alignment.

Describe a task. A fleet of agents builds it. They come back with work that is finished, tested and documented — and that agrees with itself, because none of them was allowed to contradict a decision another had already made.

Parallel agents don't scale past the human in the middle. You run five to go faster, four of them are right, the product is broken, and the only thing that catches it is you — reading everything, holding the whole picture, re-explaining choices that were already settled.

That isn't a prompting problem. Your agents have memory and they have verification, and neither answers the question that actually breaks a parallel run:

Did these two agents just settle the same question differently?

Concord Engine answers it by comparison, never by a model, and refuses the second answer at the moment it is written.

Recorded, not drawn. brag/record.mjs runs the real CLI and captures its output verbatim; brag/video.html only renders what was captured. The loop shows the refusal arc — the full run also writes the contract, binds it and briefs four workers first.

What a decision is

This is the part that gets undersold. A "decision" is not a variable name. It is any question two agents could answer differently and both be reasonable — and the cost is never the question itself, it's that nothing goes red.

Four agents implementing four reasonable answers to "what does an error body look like" produce four green test suites and one broken product. That is the whole category, and it is much wider than route paths.

The failure it stops

A refunds feature, split across a backend worker and a client worker. The backend settles the error shape. The client, working in parallel and with no visibility into the backend's files, reaches a different answer:

$ concord-engine decide --unit client --kind convention \
    --subject "error response body shape" \
    --value 'every non-2xx body is {"code":"<slug>","detail":"<message>"}' --as client

refused this contradicts a decision already in force.
  d-003  api (lead): error response body shape = every non-2xx body is {"error":"<message>"}
  because: the client shows it to a person
  yours:   every non-2xx body is {"code":"<slug>","detail":"<message>"}

  Adopt the existing value, or supersede it deliberately:
    --supersedes d-003 --layer pm      (an override, recorded as one)
    --force                            (record the disagreement for `check` to surface)

Verbatim from the recording above.

The agent is stopped at the moment it tries to disagree, and told what is in force, who decided it, why, and the two legitimate ways out. Not at integration. Not by you.

Three ways to run it

Shortened. The full README is on GitHub.

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

Concord Engine: common questions

Is Concord Engine MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Concord Engine safety report
How do I install Concord Engine?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Concord Engine need an API key?
No secret keys are declared. It reads 1 setting from the environment.
Is Concord Engine maintained?
The last commit was 12 days ago (2026-10-23). The latest release is v0.3.2.
What can I use instead of Concord Engine?
Servers from other publishers that do the same job: Argent MCP server, SvGrid MCP server and Unreal Engine MCP server.
How does Concord Engine compare with other Productivity MCP servers?
safety score 92/100 (higher than 90% of 1,299 Productivity servers); tools 12 (the typical Productivity server has 7); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Concord Engine

Same job from other publishers: the closest match first, then the best rated.

  • Argent
    Drive iOS Simulators, Android emulators, TVs and Electron/web apps from your coding agent
    A
  • SvGrid
    Checks AI-written SvGrid code against the real API, plus version-pinned Svelte 5 grid docs.
    A
  • Unreal Engine
    EngineWire: drive the Unreal Editor (UE 5.0-5.8): levels, Blueprints, UI, materials, VFX and more.
    B
  • CLEO MCP Server
    Task management for AI coding agents — CQRS 2-gateway pattern, 200 ops across 10 domains
    B
  • Joxo
    One shared project for a team's coding agents: decisions, a task board and handoffs.
    A