MCP server

Forge Engine Official

app.forgeengine/forge

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

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

Website Source

At a glance

Type

MCP server

Publisher

forgeengine.app (verified by the MCP Registry)

Status

Working at last check

Tools

54

Token cost

About 8,051 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

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

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.forge]
url = "https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp"

Gemini CLI

{"mcpServers":{"forge":{"httpUrl":"https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp"}}}

Cursor

{"mcpServers":{"forge":{"url":"https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp"}}}

VS Code

{"servers":{"forge":{"type":"http","url":"https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp"}}}

Antigravity

agy mcp add forge https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"forge","server_url":"https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"forge","server_url":"https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp"}

Tools

• add_task ~196 tokens
  Add a task to a milestone — DIRECT. assignee:"me" claims on creation.
• dedupe ~100 tokens
  Remove duplicate-named entries (keep first) — DIRECT, destructive.
• delete_entity Deletes data · ~189 tokens
  PROPOSE a delete → Inbox (owner adopts; nothing deleted now). id preferred or exact name; flow_edge may use from+to.
• design_ui_from_systems ~81 tokens
  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_balance ~93 tokens
  Read Balance Lab: stat tables, boards with EVALUATED values, scenarios.
• get_briefing ~240 tokens
  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
• get_build_region ~214 tokens
  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 p
• get_design_document ~293 tokens
  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`
• get_help ~60 tokens
  Forge how-to on demand (no project needed): propose→adopt, what a System is, Balance Lab formats, sign-in. Call when unsure.
• get_history ~130 tokens
  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_impact ~115 tokens
  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_inbox ~61 tokens
  PENDING Inbox (the owner's triage queue). Check BEFORE proposing — avoid duplicates. Read-only.
• get_milestone ~88 tokens
  ONE milestone: goal, weeks, difficulty, systems, every task (id/name/done/status/effort).
• get_project_context ~61 tokens
  FULL design dump — LARGE, last resort; prefer get_project_meta + list_*/get_*/search.
• get_project_meta ~68 tokens
  START HERE. Tiny overview: counts, members, task claims + working_now (avoid collisions), forge_workflow_version.
• get_rejections ~66 tokens
  Owner's DECLINED list — check at session start; follow each entry's guidance, then resolve_rejection(title).
• get_screen ~117 tokens
  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_image ~103 tokens
  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_stale ~165 tokens
  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
• get_system ~94 tokens
  ONE system's full spec (Goal/Boundary/Acceptance, markdown, sources, status) + pending Inbox changes touching it.
• get_workflow ~76 tokens
  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_code ~75 tokens
  One-command codebase import: recipe + batch id — propose one Context overview + one System per real module; the owner adopts all at once.
• list_activity ~143 tokens
  Change history {who, change, entity, kind, when}, newest first; filter kind/who/query.
• list_milestones ~52 tokens
  All milestones, compact: id, name, weeks, order, done/total.
• list_projects ~49 tokens
  Projects your key reaches (id, name, role); pass an id as project_id to switch.
• list_screens ~48 tokens
  All screens, compact: id, name, purpose, status.
• list_systems ~49 tokens
  All systems, compact: id, name, status, 1-line goal.
• next_task ~161 tokens
  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 cl
• post_log ~125 tokens
  Append a build-log entry to Activity — what you built/decided (commit-note style).
• propose_balance_board ~150 tokens
  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_table ~198 tokens
  Propose a stat-doc TABLE → Inbox. csv (header; `key%` = percent; first column = name) OR schema+rows. Adopting REPLACES same-named.
• propose_context ~270 tokens
  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
• propose_dna ~110 tokens
  Propose Project DNA and/or Tech Notes → Inbox (at least one).
• propose_element ~231 tokens
  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_edge ~121 tokens
  SECONDARY (user-driven UI): propose a link between two existing screens → Inbox.
• propose_milestone ~147 tokens
  Propose a NEW milestone (+ optional tasks) → Inbox.
• propose_screen ~150 tokens
  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_system ~260 tokens
  Propose a NEW system → Inbox. spec = ## Goal / ## Boundary (Owns · Doesn't own) / ## Acceptance. Exists? use update_system. (Alias: create_proposal.)
• rename_screen ~102 tokens
  Rename a screen IN PLACE — DIRECT; links/elements follow (id-referenced).
• reorder ~178 tokens
  Reorder milestones / tasks / elements — DIRECT. order = ids in new order; omitted keep relative order.
• report_build_status ~507 tokens
  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 ta
• report_drift ~140 tokens
  Flag CODE DRIFT — mapped files no longer match the repo. Advisory; a fresh report_build_status clears it.
• report_milestone_progress ~131 tokens
  Mark existing-milestone tasks done → Inbox progress card (owner adopts the ticks).
• report_screen_status ~101 tokens
  Report a SCREEN's status (todo|in-progress|implemented) → Inbox.
• resolve_rejection ~93 tokens
  Report you REVERTED a declined change (unlocks the owner's Clear). Call after realigning the build.
• resync_from_idea ~187 tokens
  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
• search ~110 tokens
  Keyword search — compact hits {kind, id, name} + snippet.
• set_design_overview ~312 tokens
  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 i
• trace_ui_from_image ~214 tokens
  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. Y
• update_element ~236 tokens
  Move/resize/relabel an element — DIRECT, live. element_id (preferred) or screen+label; x+y also places an unplaced one.
• update_milestone ~151 tokens
  Edit milestone goal/weeks/difficulty/name — DIRECT. new_name renames (never delete+recreate).
• update_system ~308 tokens
  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_task ~250 tokens
  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_proposal ~82 tokens
  Remove YOUR OWN still-pending Inbox item (id from the propose response / get_inbox).

Browse

• Converting to Markdown
• Email
• Food and recipes

Related MCP servers

• Forge Arena — Agent Wilds
  Autonomous agents create, compete, converse, vote, and build reputation in a bounded public world.
• Picorn
  Picorn turns AI briefs into editable social images and videos with layers, timelines, and renders.
• AI Design Blueprint
  Doctrine and validators for governable agentic AI products.
• MagicON RF Design Engines
  TX/RX/T-R chains, OTA link, radar, PCB filters, patch antennas, stackup, thermal, PDN, compliance.
• The Cable Code
  Decode cables in 66 coding systems; design, rate and check them; find equivalents; size drums.
• Wearmu Mu
  Official AI-native print-on-demand MCP — say it, AI designs it, sell 40+ goods, earn royalties.
• Sato Hub: Build Onchain & Crypto Agents
  Build any crypto agent: stack picks, x402 and ERC-8004 lookups, wallet-key checks, unsigned swaps.
• Voicescape — on-chain identity and tipping for AI agents
  67 tools: agent blockpages, onboarding, messaging + hire loop on Hedera. Server never holds keys.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/app.forgeengine/forge.svg)](https://aptlynx.net/servers/app.forgeengine/forge)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents