MCP.Market

Forge Engine MCP server

online · 100% uptime
by forgeengine.app·app.forgeengine/forge·v0.2.0

Design spec + milestones AI coding agents read before building; drift flagged, changes reviewed.

B76/100grade B
What users say
No reviews yet
Be the first
Safety scan
B76/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed Forge Engine yet.

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

Forge Engine tools (54, 10 write)

write = sends, deletes, buys or posts
  • add_taskFree

    Add a task to a milestone — DIRECT. assignee:"me" claims on creation.

  • dedupewrite actionFree

    Remove duplicate-named entries (keep first) — DIRECT, destructive.

  • delete_entitywrite actionFree

    PROPOSE a delete → Inbox (owner adopts; nothing deleted now). id preferred or exact name; flow_edge may use from+to.

  • design_ui_from_systemsFree

    Recipe to design the UI from Systems (user request only): steps + batch id — confirm canvas aspect, then screens + PLACED elements + edges in one batch.

  • get_balanceFree

    Read Balance Lab: stat tables, boards with EVALUATED values, scenarios.

  • get_briefingFree

    ONE-CALL orientation before you build: pass `files` you're about to edit (or a `task`) → the systems that own them, each with Goal + Acceptance + build status/files/last_commit/drift + coupled_systems (code neighbors an edit may break) + pending Inbox changes + recent decisions, plus open-rejection count, who's active, `recent_changes` (what happened since you were last here — a session handoff), and a task to claim. Replaces the get_project_meta→get_system→get_build_region dance.

  • get_build_regionFree

    System→code map per built system: implementing files, status, drift flag, last_commit, and acceptance-evidence COUNTS. Mapped files gone from the repo? report_drift. Pass `system:"<name|id>"` for ONE system plus the full text of its acceptance criteria (omitted from the map — it is the bulk of the payload). Big projects come back paged: the body says 'page N of M', call again with `page: N+1`.

  • get_design_documentFree

    The WHOLE design as one readable document — Vision (+ Project DNA) → every System spec → reference notes, compiled deterministically from the current design. Read this to understand a project end-to-end instead of walking list_systems → get_system N times. Returns markdown plus the project `version` it was compiled from. Long designs come back PAGED — the header says 'part N of M', call again with `page: N+1` for the rest. Pass `for_summary: true` to get the condensed projection instead (every system's Goal + Boundary, tables stripped, one page) — that is what you should summarize from.

  • get_helpFree

    Forge how-to on demand (no project needed): propose→adopt, what a System is, Balance Lab formats, sign-in. Call when unsure.

  • get_historyFree

    DESIGN MEMORY: recorded decisions/logs/rejections with who/when. Read BEFORE changing a system's direction; empty = no recorded WHY — don't invent one.

  • get_impactFree

    BLAST RADIUS of a system (deterministic): upstream context, siblings, dependent screens/milestones, files, code-coupled systems, pending Inbox, recent activity. Run BEFORE changing it.

  • get_inboxFree

    PENDING Inbox (the owner's triage queue). Check BEFORE proposing — avoid duplicates. Read-only.

  • get_milestoneFree

    ONE milestone: goal, weeks, difficulty, systems, every task (id/name/done/status/effort).

  • get_project_contextFree

    FULL design dump — LARGE, last resort; prefer get_project_meta + list_*/get_*/search.

  • get_project_metaFree

    START HERE. Tiny overview: counts, members, task claims + working_now (avoid collisions), forge_workflow_version.

  • get_rejectionsFree

    Owner's DECLINED list — check at session start; follow each entry's guidance, then resolve_rejection(title).

  • get_screenFree

    ONE screen's layout: canvas `resolution` (use THESE px), elements x/y/w/h, links, popups. Read before editing a screen. has_reference_image:true → get_screen_image shows you the actual image.

  • get_screen_imageFree

    A screen's reference image (HUD background) as an actual IMAGE you can see — reads the stored file inline (signed-URL fallback past 4MB).

  • get_staleFree

    What has drifted between the Idea lane and the System Specs — the design's own out-of-sync list, computed deterministically (no AI, no tokens). Three kinds: Idea notes edited since the systems were generated from them (with the systems each one touches), Idea notes whose prose the systems have moved past, and specs whose stamped source fingerprint no longer matches. Read this before assuming the design is coherent; fix the first kind with resync_from_idea.

  • get_systemFree

    ONE system's full spec (Goal/Boundary/Acceptance, markdown, sources, status) + pending Inbox changes touching it.

  • get_workflowwrite actionFree

    Run FIRST in a new repo (no project): first-connect routine + the working-agreement block to ADD to AGENTS.md/CLAUDE.md now (tell the user in one line; remove if they object).

  • import_from_codeFree

    One-command codebase import: recipe + batch id — propose one Context overview + one System per real module; the owner adopts all at once.

  • list_activityFree

    Change history {who, change, entity, kind, when}, newest first; filter kind/who/query.

  • list_milestonesFree

    All milestones, compact: id, name, weeks, order, done/total.

  • list_projectsFree

    Projects your key reaches (id, name, role); pass an id as project_id to switch.

  • list_screensFree

    All screens, compact: id, name, purpose, status.

  • list_systemsFree

    All systems, compact: id, name, status, 1-line goal.

  • next_taskFree

    DISPATCHER (multi-agent): atomically pick + claim the next task to build — walks milestones in order, skips human-only tasks and any task whose systems share code files with a task another agent already holds or is actively touching, so parallel agents spread out instead of colliding. Returns the claimed task + systems, or why none is free. dry_run:true peeks without claiming.

  • post_logwrite actionFree

    Append a build-log entry to Activity — what you built/decided (commit-note style).

  • propose_balance_boardFree

    Propose a node board → Inbox. Kinds const|formula|item|sheet|loadout|picker|pool|process|note|frame; formulas reference blocks by NAME; omit x/y = auto-layout. Adopting REPLACES same-named.

  • propose_balance_tableFree

    Propose a stat-doc TABLE → Inbox. csv (header; `key%` = percent; first column = name) OR schema+rows. Adopting REPLACES same-named.

  • propose_contextFree

    Propose a new/updated Idea note → Inbox. Title-match to update; send the COMPLETE revised text. Set resync:true ONLY when you rewrote the note FROM the current systems (get_stale lists notes the systems have moved past) — it stops the adopted note from immediately nagging to re-generate the systems it was just written from.

  • propose_dnaFree

    Propose Project DNA and/or Tech Notes → Inbox (at least one).

  • propose_elementFree

    SECONDARY (user-driven UI): propose an element onto a screen → Inbox. ALWAYS pass x/y/w/h (px on the screen's `resolution` from get_screen); no coords = unplaced pile.

  • propose_flow_edgeFree

    SECONDARY (user-driven UI): propose a link between two existing screens → Inbox.

  • propose_milestoneFree

    Propose a NEW milestone (+ optional tasks) → Inbox.

  • propose_screenFree

    SECONDARY (user-driven UI): propose a NEW screen → Inbox. parent = popup over that screen; purpose grounds AI suggestions. Whole UI? design_ui_from_systems first.

  • propose_systemFree

    Propose a NEW system → Inbox. spec = ## Goal / ## Boundary (Owns · Doesn't own) / ## Acceptance. Exists? use update_system. (Alias: create_proposal.)

  • rename_screenFree

    Rename a screen IN PLACE — DIRECT; links/elements follow (id-referenced).

  • reorderFree

    Reorder milestones / tasks / elements — DIRECT. order = ids in new order; omitted keep relative order.

  • report_build_statusFree

    Report a SYSTEM's status (todo|in-progress|implemented) — DIRECT, live. ALWAYS pass files (full list — it REPLACES); non-todo with no files shows done-but-EMPTY. 'implemented' counts as VERIFIED only when every UNIT-TESTABLE ## Acceptance bullet is backed via evidence[{criterion,proof}]; a bullet tagged [manual]/[e2e]/[ui]/[wip] is EXEMPT (verified by manual/e2e). Otherwise it's a CLAIM (verified:false) and the response names the unbacked criteria. TWO tiers: VERIFIED = a test is NAMED; GREEN (guarantee) = you RAN the test and reported `passed:true` on the evidence — green goes stale after 21 days, so re-run to keep it.

  • report_driftFree

    Flag CODE DRIFT — mapped files no longer match the repo. Advisory; a fresh report_build_status clears it.

  • report_milestone_progressFree

    Mark existing-milestone tasks done → Inbox progress card (owner adopts the ticks).

  • report_screen_statusFree

    Report a SCREEN's status (todo|in-progress|implemented) → Inbox.

  • resolve_rejectionFree

    Report you REVERTED a declined change (unlocks the owner's Clear). Call after realigning the build.

  • resync_from_ideaFree

    The recipe for re-syncing ONE changed Idea note into the specs that depend on it — the same scoped job the app's "Re-sync N systems" button does, minus the button. Returns the note, the affected specs in full, and exactly how to send the result back. You do the writing; it lands in the owner's Inbox to ADOPT. CRUCIAL: send updates with `resync:true`, or the owner adopts your fix and the design still reports it as stale.

  • searchFree

    Keyword search — compact hits {kind, id, name} + snippet.

  • set_design_overviewwrite actionFree

    Write the Design Document's Overview — the human-readable page a new team member reads first. WRITES DIRECTLY (no Inbox): it is a derived, clearly-labelled AI summary, not design truth, and the owner can clear or rewrite it in one click. HARD RULES, same as the in-app button: use ONLY facts stated in the design (call get_design_document with for_summary:true first); invent no mechanics, numbers or names; describe, never evaluate; write in the design's dominant language. Structure: `### What this is` · `### The core loop` · `### How the systems fit` (which system feeds which — the part a raw spec list cannot give) · `### Edges` (ONLY if the design states scope limits / open questions). 250-400 words, no top-level heading. Forge stamps the project version it was compiled from, so the owner is told when the design has moved past it.

  • trace_ui_from_imageFree

    SECONDARY (user-driven UI): turn a screen's REFERENCE IMAGE into placed elements. Returns the image itself plus the recipe — the canvas resolution, the fraction→pixel conversion that stops coordinates landing wrong, and what is already on the screen so a second pass updates instead of duplicating. You look at the picture and send back propose_element / update_element with x/y/w/h; it all lands in the owner's Inbox. Use when the user wants the wireframe to match a screenshot or mockup they uploaded.

  • update_elementwrite actionFree

    Move/resize/relabel an element — DIRECT, live. element_id (preferred) or screen+label; x+y also places an unplaced one.

  • update_milestonewrite actionFree

    Edit milestone goal/weeks/difficulty/name — DIRECT. new_name renames (never delete+recreate).

  • update_systemwrite actionFree

    Propose a system UPDATE → Inbox diff. get_system first; send the FULL revised spec. new_title renames; context_title+context bundles the Idea update. Set resync:true ONLY when you rewrote this spec FROM its upstream Idea (see resync_from_idea) — it re-stamps the staleness signal on adopt.

  • update_taskwrite actionFree

    Edit a task or CLAIM it — DIRECT. assignee:"me"+status:"in-progress" claims (errors if held; force:true for stale); done:true or assignee:"" releases.

  • withdraw_proposalwrite actionFree

    Remove YOUR OWN still-pending Inbox item (id from the propose response / get_inbox).

Public scan report

scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it

1 high
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 1128ms20/20
  • Tool poisoning54 tool descriptions checked15/15
  • Auth qualityopen endpoint exposes 10 write-action tools with no auth3/15
  • Maintenancelast push 56 days ago12/15
  • Maintainer identitynamespace and repository owner differ; GitHub account older than a year; website matches verified namespace7/10

Findings (1)

  • highWrite-action tools reachable without authenticationauth.open-write
Overall 76/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Forge Engine compares

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

Safety score
76/100
higher than 48% of 1,337 Media servers
Tools
54
the typical Media server has 7
Tools that change things
19%
typical: 4%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote Media server answers 100%
Response time
307 ms
faster than 54% of 862 Media servers

What its tools let an agent do: 41 read · 2 create · 9 change · 1 delete · 1 send or post

Install Forge Engine in Claude Code, Cursor or VS Code

claude mcp add --transport http forge https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp
Add to Cursor

What the publisher says

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

Forge Engine — MCP connector

Many agents. One plan. No mess.

Forge Engine is the living plan for teams that build software with AI coding agents. Agents read the design over MCP and build in parallel — claiming tasks so work never overlaps, checking what breaks before they change it, and reporting back what's actually built — in a structured plan anyone on the team can read and question, coder or not. A markdown file works for one dev; a team needs Forge.

🌐 forgeengine.app

See a real design in 10 seconds, without installing anything. A Forge

project can publish one public link that serves its whole design as plain

text — paste it into an AI chat and the assistant answers over the real thing.

See Read a design with zero setup.

What's in this repository. This is the public home of Forge's **MCP

connector**: the source of the Forge Runtime CLI (@forgeengine/cli, MIT) and

the registry manifest (server.json). The Forge application

and its hosted MCP server are developed in a separate private repository — so

this repo is the part that runs on your machine, published openly precisely

because it is the part that holds your token. See

Security & privacy.

Not to be confused with Laravel Forge (PHP server management), Atlassian

Forge / Autodesk Forge (app & CAD platforms), SourceForge (software hosting),

Minecraft Forge (a mod loader), ForgeCode, or Plan Forge. In the context of MCP

and AI coding agents, "Forge" means Forge Engine (forgeengine.app).

The problem this solves

Coding agents are fast and they are amnesiac. Every session starts blank, so the same context gets re-pasted; a decision made three sessions ago is forgotten and quietly undone; an autonomous run reaches into a working system nobody was watching. Add a second agent — or a second person driving one — and the failures compound: two agents rewrite the same module, a spec everybody believed was current turns out to describe something that shipped differently, and nobody can say which parts of the plan are actually built.

None of that is fixed by writing a better document. A document has no way to know whether it was read, no way to say "this system is off-limits", and no way to notice that the code walked away from it. Forge makes the plan a thing agents transact with: they read it before building, claim what they take, and report what they changed — and every one of those steps leaves evidence a human can check.

What the loop actually gives you

Agents start informed instead of blank. One call returns the working context for the task at hand: what this system is for, what it must not touch, what "done" means for it, and who else is currently working where. That replaces the preamble you retype every session — and unlike a pasted preamble, it is the same context every agent gets, so two agents cannot be working from two different versions of the truth.

Parallel work stops colliding. Tasks are claimed, and a claim is visible to every other agent and person on the project. An agent that reaches for occupied work is told so, by name, before it starts — not after both branches exist.

Shortened. The full README is on GitHub.

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

Forge Engine: common questions

Is Forge Engine MCP server safe?
Mostly: it is graded B (76/100). Read the Forge Engine safety report
How do I install Forge Engine?
It runs remotely at mmvdabzadclebfxyzudg.supabase.co. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Forge Engine need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Forge Engine maintained?
The last commit was 97 days ago (2026-07-30). The latest release is v0.2.0.
Is Forge Engine up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Forge Engine?
Servers from other publishers that do the same job: Buoy MCP server, Dembrandt MCP server and Codesign MCP server.
How does Forge Engine compare with other Media MCP servers?
safety score 76/100 (higher than 48% of 1,337 Media servers); tools 54 (the typical Media server has 7); tools that change things 19% (typical: 4%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Forge Engine

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

  • Buoy
    The design system your coding agents check before they ship: tokens plus exact UI fixes.
    A
  • Dembrandt
    Design tokens from any live site: colours, type, spacing, components, drift against a baseline.
    B
  • Codesign
    Local design engine for AI agents: create, edit and export real, editable designs.
    A
  • TypeUI
    Design systems, UI prompts, and layout variations for AI coding tools.
    A
  • memi
    Memi is the read-only design engineering audit and skill layer for coding agents.
    A