Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
Run sigit.si locally: browse repos, search code, manage PRs, issues, and Cloud Sessions.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
SIGIT_TOKEN, SIGIT_TOOLSETS标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
作者没有在注册中心列出安装信息。请查看下方作者的 README。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过域名 sigit.si 验证(注册中心会核实域名所有权)
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:SIGIT_TOKEN
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(1.3.0)于9天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Rust。
同一分类中有:Context7, Codebase Memory, Exa
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
si is the command line interface for sigit.si — sign in, manage repositories, review pull requests, triage issues, search code, and drive Cloud Sessions, all from the terminal.
cargo install --path crates/cli
This installs a binary named si.
si auth login # sign in with your sigit.si account
si repo list # your repositories si repo create my-project --private si repo clone seto/my-project # clone with your sign-in, no token in the URL si auth setup-git # or let plain git clone use it too
si pr list si pr view 42 si pr create --title "Fix the thing" --base main
si issue list --state open si issue create --title "Bug: ..." --body "Steps to reproduce..."
si code search "TODO" --ref main si code view README.md
si status set HEAD --state success --context ci/test si status view # the checks on HEAD
si run start --repo seto/app "Fix the failing build" si run list si run view 12 # status and the end of the transcript
si site publish --wait # publish the default branch as a site si site view
si session new --title "Refactor auth" si models si billing show
si auth signup # also: resend, reset-password, delete-account
si browse # open the current repo on sigit.si si api repos # raw escape hatch for any endpoint
Pass --json to any read command for machine-readable output.
si mcp serves these same commands to an AI agent as MCP tools over stdio:
{
"mcpServers": { "sigit": { "command": "si", "args": ["mcp"] } } }
There is nothing to authenticate — the server reuses the token si auth login stored. Point your editor at the directory of a checkout and repository tools default to the repo you're standing in, so the agent can say "list the open pull requests" without naming one; create_pull_request likewise defaults its head to the checked-out branch.
Trim the tool list when an agent doesn't need all of it:
si mcp --read-only # drop every tool that writes
si mcp --toolsets repo,issue,pr,code # or SIGIT_TOOLSETS=repo,issue
Toolsets are account, repo, issue, pr, code, hook, session, and billing. sigit.si also hosts a remote MCP server at /api/v1/mcp for clients that would rather connect over HTTP than spawn a binary.
si --environment dev repo list # a local sigit.si server (localhost:3000)
SIGIT_HOST=staging.example.com si repo list
Credentials are stored per-environment in ~/.sigit/token (or ~/.sigit-dev/token). SIGIT_TOKEN overrides the stored token, which is how CI authenticates without an interactive login.
si binary: command parsing, terminal rendering, git remote resolution, and credential storage, built on top of sigit-si-api.Issues, pull requests, and code search have no REST surface on sigit.si yet — they're served over the same MCP (Model Context Protocol) JSON-RPC endpoint the AI agent uses. sigit-si-api speaks that transport internally; it's not visible at the call site.
This repo publishes two entries to the official MCP Registry, one per way of reaching the same tools, so registry-aware clients can add either in one click:
| Listing | File | What it is |
|---|---|---|
si.sigit/cli | server.json | This CLI: a cargo package listing that runs si mcp over stdio. |
si.sigit/sigit | server-sigit.json | The hosted server at sigit.si/api/v1/mcp, a remote Streamable-HTTP listing. The endpoint sigit-si-api talks to, and the official server siGit Code bakes in. |
The CLI holds server.json because it's what this repo ships, and that's the filename mcp-publisher defaults to. Sibling listings are named after their own leaf, so the file says which entry it publishes.
Both go out through the release-mcp-registry.yml workflow, and both prove namespace ownership with a DNS TXT record on sigit.si rather than GitHub OIDC, so one credential covers the pair. A package listing has a second hurdle: the registry fetches the crate from crates.io and looks for the mcp-name: si.sigit/cli marker in its README, which is why that marker sits in this file. Crate versions are immutable, so a release that ships without the marker can never be listed, and fixing it costs a new version. The internal setup and release runbook live with the server (private sigit-si repo).
To cut a release, bump [workspace.package].version and the sigit-si-api dependency in the root Cargo.toml, merge development into main, and push a vX.Y.Z tag. release-crates.yml checks the crate versions against the tag, publishes whichever of sigit-si-api and sigit-si-cli isn't on crates.io yet (through Trusted Publishing, so no token is stored), then dispatches release-mcp-registry.yml.
make build # cargo build --workspace
make test # cargo test --workspace make lint # cargo clippy --workspace --all-targets -- -D warnings make fmt # cargo fmt --all make check # fmt + lint + test
All em dashes are written by Seto Elkahfi.
Apache-2.0