Twiceshy MCP Server

@dotts-h

代码仓库主页

基本信息

分类

其他

许可证

AGPL-3.0

传输方式

stdio

作者

dotts-h

提交者

Horia C. Rădulescu

关于 Twiceshy MCP Server

Once bitten, twice shy — a shared memory of validated engineering traps, dead-ends and fixes for coding agents, served over MCP. AGPL-3.0.

Twiceshy MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "twiceshy": {
      "type": "streamable-http",
      "url": "https://api.twiceshy.app",
      "headers": {
        "Authorization": "Bearer tok_YOUR_TOKEN_FROM_twiceshy.app"
      }
    }
  }
}

Twiceshy MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

点击上方按钮,直接连接服务器端点实时获取工具列表。

概览

What is Twiceshy?

A self‑hosted service that feeds hard‑won engineering experience — issues, dead‑ends, root causes, validated fixes — to LLM coding agents at decision time, so they stop repeating known mistakes on autopilot. It operates like a private, curated, validated StackOverflow that injects itself at the right moment.

How to use Twiceshy?

Use the hosted instance at twiceshy.app with the remote MCP endpoint https://api.twiceshy.app/, or self‑host following the development instructions (make ci). Interact via MCP tools: search_experience, get_experience (read path) and record_experience (propose‑only write path).

Key features of Twiceshy

Git‑backed markdown experience records with YAML frontmatter.
Derived SQLite index with FTS5 (dense retrieval planned).
Multi‑stage retrieval: fingerprint‑exact → BM25 → dense, with relevance floor and hard cap of 3 results.
Two channels: push (Claude Code hooks) and pull (MCP tools over streamable HTTP).
Trust model: agent‑proposed records quarantined, promoted only after sandbox validation and human PR review.
Background “doctors” for dedup, staleness, repro re‑execution, decay, and abstraction.

Use cases of Twiceshy

Prevent an agent from re‑introducing a known bug or deprecated API.
Inject verified workarounds for third‑party issues at decision time.
Record and propagate root‑cause analyses across a team.
Capture validated fixes so future agents skip dead‑end investigations.
Automatically quarantine untested proposals until they pass human review.

常见问题

What retrieval stages does Twiceshy use?

Retrieval follows a cascade: fingerprint‑exact → BM25 → dense (RRF), with stack‑fingerprint filtering and a relevance floor. At most 3 results are injected; below the floor nothing is injected.

How does Twiceshy ensure experience records are trustworthy?

Agent‑proposed records are quarantined. Promotion requires a sandbox fail‑to‑pass validation and a human‑reviewed pull request. A new record *is* a PR.

What is the license?

The Twiceshy engine is AGPL‑3.0‑only. Contributions require a signed CLA, and the corpus has a separate licensing strategy (see [ADR‑0002](docs/adr/ADR‑0002‑licensing‑strategy.md)).

What is the current status of development?

Bootstrapping. Phase 1 (read path: parser/validator, FTS5 index, fingerprint + lexical search, MCP `search_experience`/`get_experience`) is complete. Phase 3 write path (`record_experience` – propose‑only) has landed. Remaining phases (hooks push channel, dense retrieval, doctors) are tracked as issues.

其他分类下的更多 MCP 服务器

Health by Dr Brad

Dr Brad Stanfield

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one

EverArt

modelcontextprotocol

Model Context Protocol Servers

88.1K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Yuppsy

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K