Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
Nothing to run from here
Forge Engine is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
54
tools declared
—
trust score
remote
at its publisher
—
calls last 7d
What it does
Design spec + milestones AI coding agents read before building; drift flagged, changes reviewed.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http forge-engine-mcp https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp
# 2 — ask your agent for something these tools do
# get_help, get_workflow, import_from_code and 51 more
Forge Engine costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
FOAll 1 server
forgeengine1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http forge-engine-mcp https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
54 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Forge how-to on demand (no project needed): propose→adopt, what a System is, Balance Lab formats, sign-in. Call when unsure.
No parameter schema on file.
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).
No parameter schema on file.
One-command codebase import: recipe + batch id — propose one Context overview + one System per real module; the owner adopts all at once.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | no | — |
Recipe to design the UI from Systems (user request only): steps + batch id — confirm canvas aspect, then screens + PLACED elements + edges in one batch.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | no | — |
Append a build-log entry to Activity — what you built/decided (commit-note style).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | What you did / decided (1–2 sentences) |
| entity | string | no | System/screen/milestone it's about |
| version | string | no | e.g. "0.379.0" |
| project_id | string | no | — |
FULL design dump — LARGE, last resort; prefer get_project_meta + list_*/get_*/search.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | no | — |
Projects your key reaches (id, name, role); pass an id as project_id to switch.
No parameter schema on file.
START HERE. Tiny overview: counts, members, task claims + working_now (avoid collisions), forge_workflow_version.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | no | — |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| screen | string | yes | The screen whose reference image to trace (name or id) |
| project_id | string | no | — |
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 d
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | no | — |
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 sti
| Parameter | Type | Required | Notes |
|---|---|---|---|
| note | string | yes | The Idea note's title or id (from get_stale) |
| project_id | string | no | — |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| for_summary | boolean | no | Return the condensed summarization source (all system goals + boundaries, no tables) instead of the full document |
| page | number | no | Which part of the full document to return (default 1). The header tells you how many parts there are. |
| project_id | string | no | — |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| summary | string | yes | The Overview in markdown, starting at ### What this is |
| project_id | string | no | — |
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),
| Parameter | Type | Required | Notes |
|---|---|---|---|
| files | array | no | Repo-relative paths you're about to touch — mapped to their systems |
| task | string | no | A task id or name — briefs its milestone's systems instead |
| project_id | string | no | — |
ONE system's full spec (Goal/Boundary/Acceptance, markdown, sources, status) + pending Inbox changes touching it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | Preferred |
| name | string | no | If no id |
| project_id | string | no | — |
All systems, compact: id, name, status, 1-line goal.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| system | string | no | One system by name or id — returns its acceptance-criteria detail too |
| page | number | no | Which page of the map (default 1); the body tells you how many there are |
| project_id | string | no | — |
Flag CODE DRIFT — mapped files no longer match the repo. Advisory; a fresh report_build_status clears it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | Preferred |
| name | string | no | If no id |
| missing_files | array | no | Paths that no longer exist |
| note | string | no | Optional — what drifted |
| project_id | string | no | — |
DESIGN MEMORY: recorded decisions/logs/rejections with who/when. Read BEFORE changing a system's direction; empty = no recorded WHY — don't invent one.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| system | string | no | System id or exact name |
| query | string | no | Keyword filter |
| limit | number | no | Default 30, max 100 |
| project_id | string | no | — |
BLAST RADIUS of a system (deterministic): upstream context, siblings, dependent screens/milestones, files, code-coupled systems, pending Inbox, recent activity. Run BEFORE changing it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | Preferred |
| name | string | no | If no id |
| project_id | string | no | — |
Owner's DECLINED list — check at session start; follow each entry's guidance, then resolve_rejection(title).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | no | — |
Report you REVERTED a declined change (unlocks the owner's Clear). Call after realigning the build.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | Exactly as get_rejections returned it |
| project_id | string | no | — |
All screens, compact: id, name, purpose, status.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | Preferred |
| name | string | no | If no id |
| project_id | string | no | — |
A screen's reference image (HUD background) as an actual IMAGE you can see — reads the stored file inline (signed-URL fallback past 4MB).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | Preferred |
| name | string | no | If no id |
| project_id | string | no | — |
Move/resize/relabel an element — DIRECT, live. element_id (preferred) or screen+label; x+y also places an unplaced one.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| element_id | string | no | From get_screen (preferred) |
| screen | string | no | With label, if no element_id |
| label | string | no | Current label |
| x | number | no | px on the screen's canvas |
| y | number | no | — |
| w | number | no | — |
| h | number | no | — |
| new_label | string | no | Rename (optional) |
| type | string | no | e.g. button/bar/panel (optional) |
| note | string | no | "" clears |
| system | string | no | System it serves |
| project_id | string | no | — |
Remove YOUR OWN still-pending Inbox item (id from the propose response / get_inbox).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The pending item's id |
| project_id | string | no | — |
PROPOSE a delete → Inbox (owner adopts; nothing deleted now). id preferred or exact name; flow_edge may use from+to.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| kind | string | yes | What to delete |
| id | string | no | Entity/task/element/edge id |
| name | string | no | Exact name/title (if no id) |
| from | string | no | flow_edge: source screen |
| to | string | no | flow_edge: destination screen |
| project_id | string | no | — |
Remove duplicate-named entries (keep first) — DIRECT, destructive.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| kind | string | yes | What to dedupe |
| screen | string | no | For kind=elements |
| project_id | string | no | — |
Reorder milestones / tasks / elements — DIRECT. order = ids in new order; omitted keep relative order.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| kind | string | yes | What to reorder |
| order | array | yes | Ids in the new order |
| milestone_id | string | no | For kind=tasks |
| milestone | string | no | For kind=tasks (name) |
| screen | string | no | For kind=elements |
| project_id | string | no | — |
All milestones, compact: id, name, weeks, order, done/total.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | no | — |
ONE milestone: goal, weeks, difficulty, systems, every task (id/name/done/status/effort).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | Preferred |
| name | string | no | If no id |
| project_id | string | no | — |
Change history {who, change, entity, kind, when}, newest first; filter kind/who/query.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Keyword filter (optional) |
| kind | string | no | system | context | milestone | screen (optional) |
| who | string | no | Author email substring (optional) |
| limit | number | no | Default 30, max 200 |
| project_id | string | no | — |
PENDING Inbox (the owner's triage queue). Check BEFORE proposing — avoid duplicates. Read-only.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | no | — |
Keyword search — compact hits {kind, id, name} + snippet.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Text to search for |
| kinds | array | no | Optional: system | context | milestone | task | screen | proposal |
| project_id | string | no | — |
Propose a NEW system → Inbox. spec = ## Goal / ## Boundary (Owns · Doesn't own) / ## Acceptance. Exists? use update_system. (Alias: create_proposal.)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | System name (Title Case, English) |
| spec | string | yes | Markdown: ## Goal / ## Boundary / ## Acceptance |
| files | array | no | Implementing paths, ONE file per entry |
| derives_from | array | no | Context note title(s) this system derives from → wires provenance (upstream + siblings) |
| batch | string | no | import_from_code batch id |
| acknowledge_rejection | boolean | no | Only after a DECLINED bounce AND asking the user |
| project_id | string | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | Match existing to update, or new to add |
| content | string | yes | Complete text, not a delta |
| batch | string | no | import_from_code batch id |
| resync | boolean | no | This note was re-derived from the current systems — re-stamps both staleness signals on adopt |
| acknowledge_rejection | boolean | no | Only after a DECLINED bounce AND asking the user |
| project_id | string | no | — |
Propose Project DNA and/or Tech Notes → Inbox (at least one).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dna | string | no | Omit to leave unchanged |
| tech_notes | string | no | Omit to leave unchanged |
| batch | string | no | import_from_code batch id |
| project_id | string | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | Preferred |
| name | string | no | If no id |
| spec | string | yes | Full revised spec markdown |
| new_title | string | no | Rename in the same card |
| context_title | string | no | Idea section to also update |
| context | string | no | Full revised Idea text |
| resync | boolean | no | This spec was re-derived from its upstream Idea — re-stamps sourceSig on adopt. Never set it on an ordinary edit. |
| acknowledge_rejection | boolean | no | Only after a DECLINED bounce AND asking the user |
| project_id | string | no | — |
Read Balance Lab: stat tables, boards with EVALUATED values, scenarios.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| board | string | no | One board (omit = all) |
| include_rows | boolean | no | false = schema only |
| project_id | string | no | — |
Propose a stat-doc TABLE → Inbox. csv (header; key% = percent; first column = name) OR schema+rows. Adopting REPLACES same-named.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | Table name |
| csv | string | no | Header + rows; non-numeric = info |
| schema | array | no | [{key, mode: flat|pct|text, base, min, max, desc}] |
| rows | array | no | [{name, atk: 350, …}] |
| registry | boolean | no | true = the shared Stats registry |
| project_id | string | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Board name |
| nodes | array | yes | e.g. {kind:"formula",name:"dmg",formula:"atk - mdef"} |
| project_id | string | no | — |
Propose a NEW milestone (+ optional tasks) → Inbox.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Milestone name |
| goal | string | no | One-line goal (optional) |
| tasks | array | no | Task names (optional) |
| acknowledge_rejection | boolean | no | Only after a DECLINED bounce AND asking the user |
| project_id | string | no | — |
Mark existing-milestone tasks done → Inbox progress card (owner adopts the ticks).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | Preferred |
| milestone | string | no | Milestone name (if no id) |
| done_tasks | array | yes | Task names that are done |
| project_id | string | no | — |
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:
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | Preferred |
| name | string | no | If no id |
| status | string | yes | todo | in-progress | implemented |
| files | array | no | ONE file per entry (optional ' — function'); prose → decisions |
| decisions | array | no | Decisions/divergences (prose) |
| evidence | array | no | Map ## Acceptance bullets to a test/file: [{criterion, proof, passed?, at?}]. Re-send full set (replaces). proof-only = backed (claimed); passed:true = test-green (guarantee). |
| version | string | no | e.g. "0.379.0" |
| project_id | string | no | — |
SECONDARY (user-driven UI): propose a link between two existing screens → Inbox.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | string | yes | Source screen name |
| to | string | yes | Destination screen name |
| label | string | no | Transition label (optional) |
| project_id | string | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| screen | string | yes | Existing screen name |
| label | string | yes | Element label, e.g. 'HP bar' |
| type | string | no | button/bar/panel/text (default box) |
| x | number | no | Left px |
| y | number | no | Top px |
| w | number | no | Default 120 |
| h | number | no | Default 40 |
| note | string | no | — |
| system | string | no | System it serves |
| project_id | string | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Screen name (Title Case, English) |
| purpose | string | no | What this screen is for |
| parent | string | no | Make it a POPUP over this screen |
| project_id | string | no | — |
Report a SCREEN's status (todo|in-progress|implemented) → Inbox.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| screen | string | yes | Screen name |
| status | string | yes | todo | in-progress | implemented |
| project_id | string | no | — |
Rename a screen IN PLACE — DIRECT; links/elements follow (id-referenced).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Exact CURRENT name |
| new_name | string | yes | New name (must not collide) |
| project_id | string | no | — |
Edit milestone goal/weeks/difficulty/name — DIRECT. new_name renames (never delete+recreate).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | Preferred |
| name | string | no | Current name (if no id) |
| goal | string | no | — |
| weeks | number | no | — |
| new_name | string | no | Rename |
| difficulty | string | no | "" clears |
| project_id | string | no | — |
Add a task to a milestone — DIRECT. assignee:"me" claims on creation.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| milestone_id | string | no | Preferred |
| milestone | string | no | If no id |
| name | string | yes | Task name |
| done | boolean | no | — |
| status | string | no | — |
| effort | string | no | — |
| assignee | string | no | "me" claims it |
| human | boolean | no | Human-only (GTM/validation/people work) — next_task & get_briefing skip it |
| project_id | string | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dry_run | boolean | no | Peek without claiming |
| project_id | string | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task_id | string | yes | From get_milestone |
| name | string | no | — |
| done | boolean | no | true releases the claim |
| status | string | no | "" clears |
| effort | string | no | "" clears |
| assignee | string | no | "me" claims; "" releases |
| force | boolean | no | Take over a STALE claim only |
| human | boolean | no | true = human-only (next_task/get_briefing skip it); false clears |
| project_id | string | no | — |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Forge Engine or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
—Grade not published
No rule-by-rule report on file for this release
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither: the repository linked on this page is where this record was collected from, not a copy of what the address serves, so it is not graded in its place. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.2.0.
0.2.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Forge Engine can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.