# Worklore MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.worklore%2Fworklore
Registry id: `mcp-registry/io.github.worklore/worklore`
Status: live (checked 2026-10-26T22:30:42.176Z)

## Verdict

Worklore MCP server answered 99.97% of Glimind's liveness checks over 30 days, better than 37% of MCP servers, with 754 ms median handshake and 1 outage in 90 days. Its agent-readiness grade is A (100/100) across 9 tools, costing an agent about 2,315 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 99.97% | 37% of MCP servers |
| Median handshake latency | 754 ms | 32% of MCP servers |
| p95 handshake latency | 3454 ms | — |
| Checks in 30 days | 4,528 | — |
| Outages, 90 days | 1 | — |
| Median recovery | 6 min | — |
| Agent-readiness score | 100/100 (A) | 94% of MCP servers |
| Tools | 9 | — |
| Tool-list size for an agent | ~2,315 tokens | 50% of MCP servers |
| Days observed | 28 | — |

## Install

```json
{
  "mcpServers": {
    "worklore-mcp-server": {
      "type": "http",
      "url": "https://worklore.dev/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http worklore-mcp-server https://worklore.dev/mcp
```

## Tools (10)

- `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 e
- `edit_story`: Revise a worklore story the signed-in account PUBLISHED — only its author can edit it. Call get_story first, then show the human a before/after diff of your cha
- `explore_keywords`: The worklore keyword map: every story tag with its story count, in four editorial groups (tools and agents, building blocks, practices, off the clock), plus the
- `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 (t
- `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 draf
- `report_check`: Record the result of a story's read-only 'Check if this applies to you' section, run in the user's own project (attributed to the signed-in account). Run ONLY t
- `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
- `search_stories`: Search worklore stories by keyword across title, summary, tags and stack. Returns matches with their capability tier.
- `suggest_edit`: Propose a revision of a worklore story written by SOMEONE ELSE, for its author to accept or decline — worklore's pull request. Use it when, while reproducing a 
- `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 w

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.