目录 / worklore
worklore
A library of short, honest developer stories your agent can actually execute — plus a capability x-ray for anything you're about to run. Every story is something a real developer did: what they tried, what failed, what finally worked. Each one carries a machine-readable "Reproduce this" contract, so your agent can run the same fix in your own project instead of you reading a blog post and translating it by hand. Stories show how many other people's agents reproduced them successfully, and "it failed" is a reportable, published outcome — not everything transfers between stacks, and worklore says so. **check_capability** works on anything, not just worklore content: paste a Skill, a story, or untrusted prompt text and get back what it can actually touch — a capability tier (T0–T4) bound to the content's sha256, with file:line evidence — plus behavioral red flags like prompt-injection, exfiltration and safety-bypass phrasings. It's blast-radius disclosure for a human to review, never a "this is safe" verdict. **Tools:** `search_stories`, `get_story`, `suggest_for_project`, `check_capability`, `report_reproduction`, `publish_story` Sign in with GitHub — worklore only ever sees your public handle and avatar. Open source: https://github.com/worklore/worklore-mcp
接入信息
- 传输形态
- http
- 鉴权方式
- 鉴权未知
- 端点
https://worklore--worklore.run.tools
{
"mcpServers": {
"worklore": {
"url": "https://worklore--worklore.run.tools"
}
}
}
能力清单
| 工具 | 说明 |
|---|---|
| check_capability | Disclose what an agent Skill or worklore story CAN DO before you run it: a capability tier T0-T4 bound to a content sha256, with findings that carry file:line evidence, PLUS a separate list of behavioral red flags (prompt-injection / deception / exfiltration-intent / safety-bypass phrasings) for a human to review. This is blast-radius disclosure and triage, never a 'safe' verdict. Pass the raw `text`, or a `url` to fetch and scan (e.g. a worklore story .md). |
| get_story | Fetch one worklore story by slug — its full markdown (narrative + the 'Reproduce this' contract your agent would run) WITH its capability disclosure attached (tier + findings), so you see what it can do before applying it. Read the capability first; run check_capability on the live artifacts before executing. After you apply the story to the user's task, call report_reproduction with an honest result to record it. |
| search_stories | Search worklore stories by keyword across title, summary, tags and stack. Returns matches with their capability tier. |
| suggest_for_project | Given a short description of the current project (stack, what you're building, recent problems), suggest up to 3 worklore stories worth reproducing here, with why each fits and its tier. |
| report_reproduction | Call this right after you apply a worklore story's steps to the user's own task, to record the reproduction (attributed to the signed-in account). Use an honest result: 'worked', 'partial' (you produced the output but it isn't verified yet), or 'failed' — all are useful. One counted report per person per story; repeats are acknowledged, not doubled. Never report a story you did not apply. |
| publish_story | Publish a NEW worklore story as the signed-in account. worklore stories are PUBLIC and honest, so before you call this you MUST show the human the complete draft — the title, the first-person narrative, and the 'Reproduce this' contract — and get their EXPLICIT approval. Never publish on your own initiative and never invent details. Provide the full story as `markdown` (frontmatter with title/date/tags/type/reproducible, then '# title', the narrative, then '## Reproduce this' with prerequisites/inputs/steps/verify) — call get_story on an existing story first to match the format — OR provide the structured fields title + narrative (+ reproduce, tags, type, stack) and the server assembles it. SANITIZE: no secrets, employer internals, client names, or private URLs. Returns the live URL and capability tier. |
提交举报 / 纠错
侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。