Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@forge-mcp research the fall of the Roman Empire"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Front door for the erewhon code agents — a forge CLI and a forge-mcp MCP server over a fleet
of coding agents: review ensembles, parallel model comparison, research harnesses, dependency
bumping, testing loops, and an architect/worker coding pipeline.
forge <verb> [args] — run forge <verb> --help for each agent's own options.
Where tasks go: verbs that emit (audit/testing/refactor/deps, the pipeline) file into
the configured task store — a Nous Forge notebook (needs the
[nous] extra), GitHub issues with TASK_STORE_BACKEND=github, or
git-bug bugs stored in the repo itself with
TASK_STORE_BACKEND=git-bug (tasks travel with the clone — no tracker API, no server).
Models: the review/analysis ensembles run against any OpenAI-compatible endpoint (point
*_OPENAI_BASE_URL-style settings at your router); edit and task/build can also drive
Claude/OpenCode per their model settings.
MCP: research, review, book are exposed as MCP tools via forge-mcp; the rest are
CLI-only.
Example | Does |
| Iterative research: plan → research → verify → synthesize ( |
| Book-length research via generator–evaluator sprint cycles |
Related MCP server: CornMCP
Example | Does |
| PR review ensemble; |
| Adversarial multi-model audit (discover→dedup→verify); |
| Find untested behavior → file test-gap tasks ( |
| Find smells, verify safe+worthwhile, file refactor tasks |
| Nightly code review of recent commits (markdown by default; optional Nous daily-note sink) |
Example | Does |
| Same prompt, N models (2–26), compare the diffs |
| Autonomous worker: pick the top ready task, run it in the sandbox, commit ( |
| Backlog report: non-done tasks grouped by project, worker dispatch gate resolved per row; |
| Coding pipeline A0+A1 framing; |
| Orchestrator wave loop (dispatch → verify → replan); |
| Final full-quorum epic sign-off (a human merges after) |
| Dependency bumper: scan + gate; |
| Upstream sync for additive forks: fetch + merge on a sync branch in a disposable worktree; green-suite + collision-seat gates; |
| Fleet sweep over a Soft Serve instance: enumerate repos via SSH, keep workdir clones fresh, run |
Example | Does |
| Score models against frozen gold sets and print the report |
| Save a scorecard as baseline / compare a fresh one against it |
uv sync # library + CLI, no Nous
uv sync --extra nous # + the Nous task-store backend
# or as a global tool:
uv tool install --editable ~/path/to/forge # `forge` + `forge-mcp`
uv tool install --editable '~/path/to/forge[nous]' # with the Nous backendMachine-local settings (router URL, API key, project paths) live in a gitignored .env at the
repo root — every agent's settings read it when run from the repo.
Privacy tiers. Every forge call to the router carries X-Router-Privacy, and the router
enforces it on the wire (local: fleet hardware only, no overflow off-box; zdr: local or a
cloud endpoint held to zero data retention per request — OpenRouter, never OpenCode Zen; any:
no requirement of forge's own). The tier is a required argument on every executor, so no verb
can fall back to the permissive default by omission. Who sends what: research/book derive it
from the lane (--local → local, otherwise zdr; --privacy overrides); review sends
any on the frontier roster and local on the local roster (PR_REVIEW_ENSEMBLE_FRONTIER_PRIVACY
/ _LOCAL_PRIVACY); map is local unconditionally; everything else defaults to zdr via a
*_ROUTER_PRIVACY setting. A seat the tier excludes comes back from the router as a 403 the
harness reports as "refused by privacy policy" and fails over from, never retries. See
forge/shared/privacy.py.
Setting up on a work machine (Bedrock strong tiers + a local model)? See docs/RUNBOOK-work-install.md and the router recipe at docs/work/litellm-work.yaml.
Conventions. Path-based verbs (audit/testing/refactor) read files/dirs into one context
(no file tools) — scope them to a crate/module, not a whole repo. First pass any emit with
--dry-run-emit to preview volume. Emitted tasks land Spec Needed + Manual (proposals),
deduped by a stable external_ref, so re-running the same sweep never duplicates.
Apache-2.0
This server cannot be deployed
Roadmap, tasks, releases and user feedback your coding agent reads and writes over MCP.
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
Coordinate coding agents through MCP using existing AI plans, saved work, and independent checks.
Search GitHub, npm, PyPI, StackOverflow, ArXiv from one MCP — built for coding agents.
