Forge Engine is a remote MCP server that gives an AI agent 54 tools, among them add_task, dedupe, delete_entity. It answers at https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.
Design source-of-truth for AI coding agents to read a project's systems and propose changes back.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
add_task | Add a task to a milestone — DIRECT. assignee:"me" claims on creation. Inputs: milestone_id, milestone, name, done, status, effort |
dedupe | Remove duplicate-named entries (keep first) — DIRECT, destructive. Inputs: kind, screen, project_id |
delete_entity | PROPOSE a delete → Inbox (owner adopts; nothing deleted now). id preferred or exact name; flow_edge may use from+to. Inputs: kind, id, name, from, to, project_id |
design_ui_from_systems | Recipe to design the UI from Systems (user request only): steps + batch id — confirm canvas aspect, then screens + PLACED elements + edges in one batch. Inputs: project_id |
get_balance | Read Balance Lab: stat tables, boards with EVALUATED values, scenarios. Inputs: board, include_rows, project_id |
get_briefing | 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) + pe Inputs: files, task, project_id |
get_build_region | 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 accepta Inputs: system, page, project_id |
get_design_document | 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 Inputs: for_summary, page, project_id |
get_help | Forge how-to on demand (no project needed): propose→adopt, what a System is, Balance Lab formats, sign-in. Call when unsure. |
get_history | DESIGN MEMORY: recorded decisions/logs/rejections with who/when. Read BEFORE changing a system's direction; empty = no recorded WHY — don't invent one. Inputs: system, query, limit, project_id |
get_impact | BLAST RADIUS of a system (deterministic): upstream context, siblings, dependent screens/milestones, files, code-coupled systems, pending Inbox, recent activity. Run BEFORE changing it. Inputs: id, name, project_id |
get_inbox | PENDING Inbox (the owner's triage queue). Check BEFORE proposing — avoid duplicates. Read-only. Inputs: project_id |
get_milestone | ONE milestone: goal, weeks, difficulty, systems, every task (id/name/done/status/effort). Inputs: id, name, project_id |
get_project_context | FULL design dump — LARGE, last resort; prefer get_project_meta + list_*/get_*/search. Inputs: project_id |
get_project_meta | START HERE. Tiny overview: counts, members, task claims + working_now (avoid collisions), forge_workflow_version. Inputs: project_id |
get_rejections | Owner's DECLINED list — check at session start; follow each entry's guidance, then resolve_rejection(title). Inputs: project_id |
get_screen | 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. Inputs: id, name, project_id |
get_screen_image | A screen's reference image (HUD background) as an actual IMAGE you can see — reads the stored file inline (signed-URL fallback past 4MB). Inputs: id, name, project_id |
get_stale | 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 Inputs: project_id |
get_system | ONE system's full spec (Goal/Boundary/Acceptance, markdown, sources, status) + pending Inbox changes touching it. Inputs: id, name, project_id |
get_workflow | 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 | One-command codebase import: recipe + batch id — propose one Context overview + one System per real module; the owner adopts all at once. Inputs: project_id |
list_activity | Change history {who, change, entity, kind, when}, newest first; filter kind/who/query. Inputs: query, kind, who, limit, project_id |
list_milestones | All milestones, compact: id, name, weeks, order, done/total. Inputs: project_id |
list_projects | Projects your key reaches (id, name, role); pass an id as project_id to switch. |
list_screens | All screens, compact: id, name, purpose, status. Inputs: project_id |
list_systems | All systems, compact: id, name, status, 1-line goal. Inputs: project_id |
next_task | 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 par Inputs: dry_run, project_id |
post_log | Append a build-log entry to Activity — what you built/decided (commit-note style). Inputs: text, entity, version, project_id |
propose_balance_board | 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. Inputs: name, nodes, project_id |
propose_balance_table | Propose a stat-doc TABLE → Inbox. csv (header; `key%` = percent; first column = name) OR schema+rows. Adopting REPLACES same-named. Inputs: title, csv, schema, rows, registry, project_id |
propose_context | 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 adopt Inputs: title, content, batch, resync, acknowledge_rejection, project_id |
propose_dna | Propose Project DNA and/or Tech Notes → Inbox (at least one). Inputs: dna, tech_notes, batch, project_id |
propose_element | 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. Inputs: screen, label, type, x, y, w |
propose_flow_edge | SECONDARY (user-driven UI): propose a link between two existing screens → Inbox. Inputs: from, to, label, project_id |
propose_milestone | Propose a NEW milestone (+ optional tasks) → Inbox. Inputs: name, goal, tasks, acknowledge_rejection, project_id |
propose_screen | 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. Inputs: name, purpose, parent, project_id |
propose_system | Propose a NEW system → Inbox. spec = ## Goal / ## Boundary (Owns · Doesn't own) / ## Acceptance. Exists? use update_system. (Alias: create_proposal.) Inputs: title, spec, files, derives_from, batch, acknowledge_rejection |
rename_screen | Rename a screen IN PLACE — DIRECT; links/elements follow (id-referenced). Inputs: name, new_name, project_id |
reorder | Reorder milestones / tasks / elements — DIRECT. order = ids in new order; omitted keep relative order. Inputs: kind, order, milestone_id, milestone, screen, project_id |
report_build_status, report_drift, report_milestone_progress, report_screen_status, resolve_rejection, resync_from_idea, search, set_design_overview, trace_ui_from_image, update_element, update_milestone, update_system, update_task, withdraw_proposal
Every block below points at https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp. Pick your client and copy.
claude mcp add --transport http forge-engine https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp
{
"mcpServers": {
"forge-engine": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp"]
}
}
}{
"mcpServers": {
"forge-engine": {
"url": "https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp"
}
}
}{
"servers": {
"forge-engine": {
"type": "http",
"url": "https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp"
}
}
}{
"context_servers": {
"forge-engine": {
"url": "https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp"
}
}
}{
"mcpServers": {
"forge-engine": {
"serverUrl": "https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp"
}
}
}{
"mcpServers": {
"forge-engine": {
"url": "https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp"
}
}
}name: Forge Engine
version: 0.0.1
schema: v1
mcpServers:
- name: Forge Engine
type: streamable-http
url: https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp{
"mcpServers": {
"forge-engine": {
"httpUrl": "https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp"
}
}
}{
"mcpServers": {
"forge-engine": {
"type": "http",
"url": "https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp"
}
}
}{
"mcpServers": {
"forge-engine": {
"url": "https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmmvdabzadclebfxyzudg.supabase.co%2Ffunctions%2Fv1%2Fforge-mcp&type=streamable_http&id=forge-engine&name=Forge%20Engine
It answered our last check on 17 October 2026 in 282 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
54, as returned by the server's own tools/list on 9 September 2026: add_task, dedupe, delete_entity, design_ui_from_systems, get_balance, get_briefing, get_build_region, get_design_document, and 46 more.
It answered our last check on 17 October 2026 in 282 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: app.forgeengine. Endpoint host: mmvdabzadclebfxyzudg.supabase.co. ARD identifier: urn:air:app.forgeengine:mcp:forge.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.