# io.github.CoralLips/gft-mcp (npm · gft-mcp)

Bring your GFT (Git for Thought) white-box thinking map to any AI agent. 把你的思维脉络接给任何 agent。

- Trust score: 74/100 (medium)
- Change this week: +10
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-15

## Components

- npm · `gft-mcp`: 74/100 (this document), [markdown](https://verifymcp.io/servers/corallips-gft-mcp/gft-mcp.md), [page](https://verifymcp.io/servers/corallips-gft-mcp/gft-mcp)

## Channel facts

- Registry: `npm`
- Package: `gft-mcp`
- Version: `0.1.4`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-15.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 104 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 7 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 81/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 728 tokens (~242/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add corallips-gft-mcp -- npx -y gft-mcp
```

### Codex

```bash
codex mcp add corallips-gft-mcp -- npx -y gft-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "corallips-gft-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "gft-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add corallips-gft-mcp --command npx --arg -y --arg gft-mcp
```

### Hermes

```yaml
mcp_servers:
  corallips-gft-mcp:
    command: "npx"
    args: ["-y", "gft-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "corallips-gft-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "gft-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-15 (score 74, +4)

- [functional regression] Security disclosure: unverified → fail
- [functional improvement] Stability: unverified → 0.27

### 2026-08-14 (score 70, 0)

- [functional regression] Security disclosure: fail → unverified

### 2026-08-11 (score 70, +6)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-08-07 (score 64)

First indexed and scored.

## MCP tools (3)

### `list_thinking_maps` (~98 tokens)

列出用户在 GFT 的全部思维脉络：图名、判断条数、各线新鲜度（哪条线最后什么时候喂过图）。
什么时候调用：本场还没链接任何脉络、需要帮用户选图时；或用户问"我有哪些脉络"。
轻查询,不含节点内容——选定后用 read_thinking_map 读取。

### `read_thinking_map` (~326 tokens)

读取用户在 GFT（gitforthought.com）里逐条确认过的思考资产——他的「思维脉络」：已经想通的判断、还悬着的问题、已经否决的方向。
什么时候调用：用户提到他之前的判断/想法/正在纠结的问题时；或你要给出建议、而这个建议应该建立在他已有的思考之上时；或他直接说「读一下我的脉络」时。
一场会话拉一次即可——内容不会在对话中途改变，反复调用只是浪费用户的 token。
选图：本场聊过哪张就继续用哪张；语境不明且用户没指名时，把返回里列出的可选项目报给用户挑，**不要赌"最近更新的那张"**——那可能是用户在别的 session 里喂的图。
若用户要把这场对话的新判断存进脉络，用 for_update=true 再调一次：会额外返回抽取规则和旧图别名，按那份规则抽完再调 submit_map_update。

Input parameters:

- `for_update` (boolean): 要往脉络里补新判断时传 true，会附带抽取规则与旧图别名。默认 false。
- `project` (string): 按项目名模糊匹配指定读哪张脉络。不传 = 最近更新的那张（多数情况不用传）。

### `submit_map_update` (~304 tokens)

把这场对话里长出来的新判断增量并入用户的思维脉络。
\**必须先调 read_thinking_map(for_update=true)**，拿到抽取规则和旧图别名，按那份规则抽出 <node/> / <edge/> 标签后，原样传进 tags。
规则由 GFT 定，你只出算力：只抽用户真说了的判断，你自己的分析除非他明确接住否则不上图；旧节点一律不重输出；没有新东西就传 <noop/>。

Input parameters:

- `agent_id` (string): 你这条对话线的稳定标识（如工作目录名或话题名）。同一张图可能被多个 session 喂,水位按此分开记,别省略。
- `cursor` (string): 本次抽到哪的标记，下次接着走。例："2026-08-05 关于 MCP 外接的讨论，至第 40 轮"。
- `project` (string): 写进哪张脉络，同 read_thinking_map。不传 = 最近更新的那张。
- `tags` (string, required): 按规则抽出的标签原文，一行一个，如：<node id="m1" title="..." body="..."/> 与 <edge from="n2" to="m1"/>。没有新东西时传 <noop/>。

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/corallips-gft-mcp/gft-mcp#diagnostics

## Score history

- 2026-08-15: 74
- 2026-08-14: 70
- 2026-08-13: 70
- 2026-08-12: 70
- 2026-08-11: 70
- 2026-08-10: 64
- 2026-08-09: 64
- 2026-08-08: 64
- 2026-08-07: 64

## Links

- npm package: https://www.npmjs.com/package/gft-mcp
- Socket report: https://socket.dev/npm/package/gft-mcp
- Repository: https://github.com/CoralLips/gft-mcp
- Changelog RSS feed: https://verifymcp.io/servers/corallips-gft-mcp/gft-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/corallips-gft-mcp/gft-mcp.json
- HTML version of this page: https://verifymcp.io/servers/corallips-gft-mcp/gft-mcp