
repoctx
io.github.nugehsPublished by GitHub account nugehsv2.6.0Updated Oct 25, 2026
Local-first code context, impact analysis, and merge-readiness verdicts for AI agents.
Overview
A local-first MCP server that gives an AI assistant deterministic repository context, change-impact ranking, and merge-readiness verdicts without sending code,
- What you can do
- Inspect and map a repository, and index or search local projects by task intent without embeddings or network calls. Build task-aware context packets naming the files, tests and commands a request needs. Rank the blast radius of a change and score how far a diff departs from the stated intent, with a receipt bound to the exact tree. Record the files a request is expected to touch and gate the staged tree, naming undeclared files and flagging secret paths and risk-sensitive changes. Produce review context, verdicts, workspace reports across repos, agent-experience scores, model-tier recommendations and agent harness files.
- When to use it
- Use it when an agent edits real repositories and you want a local, repeatable check on what a change touches and whether it is ready to merge. It suits teams that want deterministic, model-free evidence beside Claude Code, Codex, Cursor or similar hosts, and that prefer no account or hosted service.
- Requirements
- Runs as a local stdio process on the user's machine, installed from the npm package or started with npx, so Node.js is needed. It reads the local Git repository and its staged tree; no account, API key, environment variable or header is declared. The README notes an optional online mode and optional hosted pieces, but the core commands need no network.
Installation
In SourceWeft
- Open repoctx in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Solumbe
Models generate the change. Solumbe proves whether it is safe to merge.
Formerly Òtítọ́ (@bashbop/otito), renamed in 4.0.0; the CHANGELOG maps every old name to its new one.
[CI] [npm] [license: MIT] [node] [Listed on mcpservers.org] [Solumbe MCP server – quality and maintenance score on Glama]
[Solumbe MCP server – quality and maintenance score on Glama]
Solumbe is a local-first, deterministic, model-agnostic trust layer for AI-assisted development. It builds task-aware repository context before an agent edits, scores how much a change actually touches, and gates merge readiness against the exact staged tree, with no server, no account, and no code leaving the machine.
It does not replace Claude Code, Codex, Cursor, Gemini, or any native agent harness. It runs beside them and keeps working as the models change underneath.
A passing local gate is never an automatic merge approval: hosted CI, GitHub review, CODEOWNERS, and the human release decision remain separate authorities.
Install
The last command connects Solumbe's MCP server to every agent host it finds: Claude Code, Claude Desktop, Codex CLI, Cursor, VS Code, Gemini CLI and Kimi Code CLI. Add --dry-run to see the plan first, or name hosts with --host claude-code,cursor. Restart each host afterwards.
Or without installing: npx -y @bashbop/solumbe doctor.
What it does
Rank what a change actually touches, from the request alone, with no model, no embeddings, and no network:
Gate the exact staged tree, and say precisely why:
The convergence score is the part a model cannot grade for itself: it compares the stated intent against the files the diff actually changed, and produces a receipt bound to the exact base, parent, and staged-tree identity.
Hold the change to what was declared. Record the files a request is expected to touch before the edit, and the gate names any file that was never declared:
An amendment adds a file with its reason, hashed onto the contract, so a reviewer reads why the scope grew. Over MCP it is change_impact with declare: true, and review_gate with intent.
The core
Four commands are the product. They call no model, open no socket, and read nothing outside the repository.
solumbe help shows these and how to set up; solumbe help --all lists every command, including the ones that support them (impact, declare, pr, review, map, calibrate, route, ax, dashboard and the rest). Nothing was removed.
Nothing hosted is required, and nothing hosted can change a verdict. Local Core, Optional Hosted lists exactly what the optional pieces send, and where.
Supporting commands
Every command takes --json, and solumbe help lists the full set with flags.
MCP
Solumbe ships a stdio MCP server exposing 14 tools: repo_inspect, repo_map, repo_index, repo_search, context_pack, change_impact, agent_experience, model_route, convergence_score, review_context, review_gate, review_verdict, workspace_report, and repo_harness.
solumbe install --host all writes this entry for you, using absolute paths so hosts that do not inherit your shell PATH can still start it. Published in the MCP Registry as io.github.BASHBOP/solumbe. Repo-map lookups use an external per-user cache and never write into the inspected repository. Host-specific setup for Claude Code, Claude Desktop, Codex, Cursor, VS Code, Gemini CLI, and Kimi Code is in MCP and Agent Workflows.
How it compares
Documentation
Full command reference, agent workflows, release process, evaluation method, and the design theses behind the trust layer:
Contributing
npm run ci is the full gate: format, lint, typecheck, version check, tests, coverage floors (70% lines / 60% branches / 75% functions), three evaluation corpora, dependency audit, and a packaged-tarball smoke test. Run it before requesting review.
Start with CONTRIBUTING.md and the Code of Conduct. All changes need maintainer review; main requires passing gates and resolved conversations. Solumbe follows Semantic Versioning, so say whether a PR is no-impact, patch, minor, or major.
Part of the toolchain
solumbe is one of four tools that form a deterministic trust layer for AI-assisted development. Each uses static analysis to answer a question people keep handing to an LLM.
- solumbe (this tool), for context: what does this change actually touch?
- tieline, for contracts: did the front end and back end quietly stop agreeing?
- bouncer, for compliance: could you defend this to Ofcom?
- aiglare, for governance: where can the model do something you can't undo?
More at segunolumbe.com. static analysis, never the model.
Source: README.md at commit 02eaad0
Tools
0Version history
1- v2.6.0LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts