ask-kit
Reads past GitHub Copilot CLI session transcripts from local storage and can use a Copilot subscription as the investigator model, with usage counted as Copilot premium requests.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Most of a coding agent's context goes on finding things out: searching, opening files, following calls, checking what was tried before. All of it stays in the context, and it crowds out the real work.
ask-kit moves that work out of the agent's context. It gives the agent one tool, ask. The
agent asks a question in plain words, and a cheap investigator works it out in its own context.
The agent gets back a short answer, with the evidence it's based on. Your main agent keeps its
context for the heavy lifting.
you: add a CSV exporter like the other ones
agent → ask: how are the exporters built and registered, and which tests cover them?
ask → Exporters implement Exporter in src/export/base.ts:12 and are registered in
src/export/index.ts:30. JsonExporter (src/export/json.ts) is the closest model;
tests are in test/export/*.test.ts.
[code · glm-5.3-flash · 21s · $0.0031](This is an example of what an answer looks like. Measured has real numbers.)
ask is an MCP server, so any agent that takes MCP servers
can use it: Claude Code, Codex, GitHub Copilot CLI, Gemini CLI, opencode.
Read the guide: how to use it, use cases, models, tuning.
The work happens in code
The investigator doesn't work by calling tools one at a time. It writes a small JavaScript program for each step of the question, and runs it in a REPL. The program has whatever the step needs: loops, filters, joins, counts, comparisons, parsing. The logic is written fresh for that question. A domain only gives the programs a way in to the data. One program does what would otherwise take a dozen tool calls, and only what it prints comes back.
Each thing ask can answer about is a domain. ask-kit comes with two, as a starting point:
code: the repository the agent is working in, cited as
path:line.sessions: your past agent sessions, from the transcripts Claude Code, Codex, Copilot CLI, Gemini CLI and opencode already save. No proxy, no database.
Add your own for anything else your agent keeps digging through.
Related MCP server: RepoNav
Set it up
Paste one line into the agent you already use, on Linux, macOS or Windows:
Read https://github.com/temet-ai/ask-kit/blob/main/AGENTS.md, then set up ask-kit for me.The agent installs ask-kit and asks you a few questions. The main one is which model does the digging:
an API key (cheapest and fastest),
a subscription you already pay for (Claude Code, Codex, Copilot),
or a local model.
It shows what it will change before it changes anything. Restart your agents afterwards, and
they call ask by themselves when they need to find something out.
Without an agent: npm install -g --allow-git=root github:temet-ai/ask-kit, then ask-kit init
and ask-kit setup. It needs Node.js 22.13 or newer and git.
Set it up has the details.
Measured
How much context one ask keeps out of the calling agent. These are medians from mike-ask, the proof of concept ask-kit grew from:
ask-kit itself, on 18 Nov 2026, on one machine with about 1,500 sessions on disk:
Question | Investigator | Time | Cost |
What did a Codex session find and change | glm-5.3-flash (OpenRouter) | 16 s | $0.0022 |
Which sessions worked on X in the last week | glm-5.3-flash, domain picked by the router | 53 s | $0.0083 |
Follow-up on that ( | glm-5.3-flash | 17 s | $0.0035 |
Which Copilot session did a piece of work, under which ticket | Claude Code, haiku | 23 s | $0.0025 |
same | Codex (ChatGPT plan) | 36 s | in the plan |
same | Copilot CLI | 134 s | Copilot premium requests |
How does routing work in this repo | deepseek-v4.1-flash (code) | 110 s | $0.0033 |
What's in this repository
Folder | What |
| the |
| the two built-in domains, |
| what |
| the guide, also at temet.ai/docs/ask-kit |
Status
Early. Tested on Linux with real transcripts. Fixtures for all five transcript formats run in CI
on Linux, macOS and Windows. The Gemini CLI reader and the opencode and Gemini install formats
follow their docs, but haven't yet been tried on a real install. There are no releases yet, so
you install from main.
ask-kit started as mike-ask, a proof of concept that answers from what mike records of every Claude Code session. ask-kit is the general version. It needs no mike and no server.
What it stores and sends
It sends your question, and the excerpts the investigator reads, to the model you chose. There's
no telemetry. Everything it keeps is under ~/.config/ask-kit/ and ~/.local/state/ask-kit/.
What it stores and sends has the full list.
Contributing
Bug reports and small fixes are welcome; see CONTRIBUTING.md. Report security problems privately, as SECURITY.md says.
Licence
MIT, see LICENSE. Third-party licences are in THIRD-PARTY-NOTICES.md.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Retrieve citation-ready technical context and coordinate evidence-backed work between AI agents.
Collaborative, cache-first web search for agents — cited answers from a shared live-web pool.
Read reusable technical experience from other AI agents. Search a real problem with search_memories, then inspect_memory for provenance, evidence, reported outcomes and limitations. Seven anonymous read-only tools also support public agent discovery and Trust Passport inspection/verification. No account or credentials; no publishing, feedback or Candy actions on this endpoint. Operational telemetry may be recorded, but /mcp/chatgpt does not store search query text. Confidence and cryptographic integrity are not proof of truth, safety or independent validation. Writing requires the separate Remnant Agent OAuth connection at https://remnant.dedale-bi.com/mcp/agent-connect. Documentation: https://remnant.dedale-bi.com/connect. Apache-2.0 integration code and examples: https://github.com/Dedale-Project/remnant-connect. The hosted service, backend and knowledge are governed separately.
Ask any GitHub repository a question. Get source-backed answers.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAgent-native developer Q&A service providing MCP tooling and A2A runtime endpoints for deep research and citations.2MIT
- AlicenseNot gradedqualityCmaintenanceEnables locating evidence for repository questions using CodeGraph or ripgrep, providing verified results and follow-ups.8 npmMIT
- FlicenseNot gradedqualityBmaintenanceEnables coding agents to perform read-only source investigation via a local SQLite index, offering status, search, backlog, context, impact, and drift tools for TypeScript, JavaScript, and Java codebases.-
- AlicenseAqualityBmaintenanceEnables coding agents to analyze a repository evidence-first, answering questions as verifiable claims with source evidence, targeted test observations, and reference resolution.53Apache 2.0