git: git_log description doesn't say results are newest-first or that timestamp filters are optional; small models filter to an empty window
维护者通常 1 天内回复
还没有人认领这个 Issue。
评估
- 难度
- 1/5
- 预计耗时
- 1 小时以内
- 新手友好度
- 88/100
- Issue 类型
- 文档
- 描述清晰度
- 描述清楚
- 活跃度
- 活跃
- 技术栈
- git, typescript
- 领域
- devtools
调研方向
找到 git_log 工具的定义并阅读其当前描述。更新描述,说明结果按时间从新到旧排列,并且 start_timestamp 和 end_timestamp 是可选的日期范围筛选条件,使用 issue 中建议的措辞。描述清楚传达这两点后即为完成;issue 没有指定要运行的测试。
由索引模型根据 Issue 内容生成。
描述
Which server?
git (mcp-server-git)
Protocol era
Both, or not era-specific
MCP client
Custom SDK client: AgentGrade (open-source eval harness on the MCP Python SDK 2.3.0 client); model qwen3:4b-instruct via Ollama, temperature 0.7
The problem
Server: mcp-server-git==2026.10.10 (checked: 2026.11.11 has the same git_log description and the same empty output). Run with uvx mcp-server-git --repository <repo>, stdio, macOS.
git_log's description is "Shows the commit logs". It doesn't say results come newest first, or that start_timestamp / end_timestamp are optional. Asked "Who made the most recent commit on the main branch?", a small model repeatedly called:
{"repo_path": "<repo>", "max_count": 1, "start_timestamp": "now", "end_timestamp": "now"}
The server returned an empty Commit history: and the agent concluded "the commit history is empty… unknown author". This happened in 5 of 6 runs of that question (two independent runs), even when the agent knew the correct repo path.
Measured on a deterministic repository (identical commit hashes every run), 5 read-only questions x 3 runs, answers checked in code, no LLM judge.
Case study (method, all tables, caveats): https://github.com/Tanishq67m/AgentGrade/blob/main/docs/CASE_STUDY.md
Raw reports: https://github.com/Tanishq67m/AgentGrade/tree/main/results
Solution you have in mind (optional)
Change only git_log's description to something like:
Shows the commit log, newest commit first. To see the latest commits, call it with just repo_path (and optionally max_count). start_timestamp and end_timestamp are OPTIONAL filters for a specific date range - leave them out unless the user asks about particular dates, because a narrow range returns no commits.
With only that change, the suite went from 13/15 to 15/15, and the "most recent commit" question from 1/6 to 3/3.
Two smaller ideas in the same spirit:
- When no commits match, say so with a hint ("No commits in this range; omit the timestamps to see the latest commits") instead of an empty
Commit history:. - The
repo_patherror already names the allowed repository, which is great, but small models usually stopped there instead of retrying (all 9 failures in one run), and a 120B model mis-copied the long path twice. A defaultrepo_path(the configured--repository) would remove that failure class.
(We also hit git_diff rejecting main..feature in 2026.10.10. Thanks for already fixing that in #5194.)
Which MCP feature does it demonstrate? (optional)
No response
Alternatives or workarounds you have tried
- Agent-side prompt advice ("If a tool returns an error, read it and retry"): 8/15 vs 7/15 baseline, so no real effect, and it made another task worse.
- Telling the agent the repo path in its system prompt: 7/15 → 13/15 overall, but the "most recent commit" question stayed at 1/6. The timestamp trap is independent of the path.
- A larger model (gpt-oss-120b) never used the timestamp filters and scored 14/15, so this mainly affects small, cheap models.
Already built it locally?
No server code was changed. The suggested description was tested by having the client show the model only a different git_log description, with the server binary unchanged and the same tasks and repeats. Verified by deterministic, code-checked answers over 15 runs per variant. The exact text is in "Solution" above.
Before you submit
- I searched existing issues and this is not a duplicate.
- This is a request for this repository or one of its servers, not a new server, the MCP specification or an SDK.
- 主要语言
- TypeScript
- 星标
- 92k
- 派生
- 12k
- 平均合并
- 3 小时 12 分钟
- 30 天内合并 PR
- 174
环境准备
- 没有 Dockerfile 或 Docker Compose 文件
- 有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue,再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库,在一个分支上完成修改。
- 提交 Pull Request,并在描述里引用这个 Issue 编号。
modelcontextprotocol/servers 的其他 Issue
-
bug server-time v2
难度 2/5 1-3 小时 新手友好度 76/100
modelcontextprotocol/servers#5559 ·
维护者通常 1 天内回复
-
enhancement server-filesystem v2
难度 2/5 1-3 小时 新手友好度 68/100
modelcontextprotocol/servers#5553 · 2 条评论 ·
维护者通常 1 天内回复
-
chore dependencies server-fetch v2
难度 2/5 1-3 小时 新手友好度 65/100
modelcontextprotocol/servers#5546 · 2 条评论 ·
维护者通常 1 天内回复
-
chore dependencies v2
难度 2/5 1-3 小时 新手友好度 68/100
modelcontextprotocol/servers#5545 · 1 条评论 ·
维护者通常 1 天内回复
-
chore server-everything v2
难度 2/5 1-3 小时 新手友好度 86/100
modelcontextprotocol/servers#5542 · 1 条评论 ·
维护者通常 1 天内回复
查看 modelcontextprotocol/servers 的全部 Issue
相似的 Issue
-
难度 1/5 1 小时以内 新手友好度 95/100
marimo-team/marimo#11949 ·
维护者通常 1 天内回复
-
bug
难度 1/5 1 小时以内 新手友好度 88/100
Monsieur-Nico/textConvert#479 · 1 条评论 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 82/100
router-for-me/Home-Management-Center#232 ·
维护者通常 1 天内回复
-
clawsweeper:source-repro impact:ux-friction issue-rating: 🦞 diamond lobster maturity:stable P3
难度 2/5 1-3 小时 新手友好度 72/100
openclaw/openclaw#200937 · 1 条评论 · 1 个 reaction ·
维护者通常 1 天内回复
-
bug follow-up
难度 2/5 1-3 小时 新手友好度 88/100
维护者通常 1 天内回复