GitHub Code MCP
Enables read access to GitHub source code, including code search, file contents, symbols, and Java-aware fragment extraction, with optional per-call repository overrides.
README
GitHub Code MCP
An MCP server that gives the Rapid7 SI Triage agent read access to source code
on GitHub — by default, anands-bounteous/nexpose.
It fills the gap the other two servers don't cover: jira-confluence-mcp owns
tickets/KB, log-intelligence-mcp owns log retrieval, but a Phase 2
investigation also needs to pull the actual Java source that produced a stack
trace or defect. This server hits the real GitHub REST + Search APIs directly
(no mocking, no local cloning) and is scoped specifically to reading code
and returning fragments of it — issue/PR management stays out of scope.
owner/repo are optional per-call overrides on every tool, on top of the
GITHUB_OWNER/GITHUB_REPO defaults, so the server can be pointed at another
repo without a restart.
Tools
| Tool | Purpose |
|---|---|
search_code(query, path?, extension?, max_results=10, owner?, repo?) |
The core "fetch fragments for input text" tool — GitHub code search with highlighted match fragments showing exactly where the query hit. Requires GITHUB_TOKEN (GitHub rejects unauthenticated code search). |
get_file_contents(path, ref?, start_line?, end_line?, owner?, repo?) |
Fetch a file, or just a 1-indexed inclusive line range of it. |
list_symbols(path, ref?, owner?, repo?) |
Enumerate the classes/interfaces/enums/records/methods/constructors declared in a Java file, with line ranges — use this to find a symbol name for get_code_fragment. |
get_code_fragment(path, symbol, ref?, owner?, repo?) |
Java-aware extraction of one method/class/constructor body by name. Falls back to a plain text context window if the symbol isn't a recognisable declaration. |
list_directory(path="", ref?, owner?, repo?) |
Browse the repo tree. |
get_repository_info(owner?, repo?) |
Description, default branch, language, topics, stars. |
get_readme(ref?, owner?, repo?) |
Project overview as plain text. |
list_branches(max_results=25, owner?, repo?) |
Branch names + latest commit sha. |
list_commits(path?, max_results=10, owner?, repo?) |
Recent history, optionally scoped to one file. |
Java-aware fragment extraction
get_code_fragment/list_symbols are backed by a pluggable FRAGMENT_BACKEND:
tree-sitter(AST-accurate) — parses withtree-sitter+tree-sitter-java. Correctly handles generics (Map<String, List<Foo>>), annotations, records, nested/anonymous classes, and text blocks — anything a hand-rolled brace-counter gets wrong on real Java. Optional dependency:pip install -e ".[java]".regex(dependency-free fallback) — matches Java declaration syntax to find a symbol's header line, then a string/char/comment-aware balanced-brace scanner (aware of",',//,/* */, and Java 15+"""text blocks, so a{/}inside a literal or comment can't throw off the count) finds the matching close.auto(default) — triestree-sitterfirst; if the optional dependency isn't installed, logs a warning and degrades toregex. Explicit choices (tree-sitter/regex) raise instead of silently degrading.
If a requested symbol isn't a recognisable Java declaration (e.g. it's a field
name, or doesn't exist), both backends fall back to a plain
±FRAGMENT_CONTEXT_LINES text window around its first literal occurrence, with
match_type="context_window" in the response so the caller can tell it's a
lower-confidence result rather than an exact definition.
Auth & configuration
Copy .env.example to .env:
GITHUB_TOKEN=<create at github.com/settings/tokens>
GITHUB_API_BASE_URL=https://api.github.com
GITHUB_OWNER=anands-bounteous
GITHUB_REPO=nexpose
GITHUB_DEFAULT_REF=
MAX_FILE_KB=500
FRAGMENT_CONTEXT_LINES=20
FRAGMENT_BACKEND=auto
HTTP_TIMEOUT=30
HTTP_MAX_RETRIES=4
MCP_HTTP_HOST=127.0.0.1
MCP_HTTP_PORT=8082
GITHUB_TOKEN is a GitHub personal access token
(github.com/settings/tokens). It's optional for reading public repos — but
required for search_code (GitHub's code search API rejects unauthenticated
requests outright) and strongly recommended for everything else (5,000
requests/hour authenticated vs. 60/hour anonymous). A fine-grained PAT with
read-only "Contents" access is enough; no repo write scope is needed since
this server never writes to GitHub.
GITHUB_API_BASE_URL is overridable for GitHub Enterprise Server. It's
normalised to just the scheme+host, same as any pasted API URL.
The HTTP client retries 429/5xx with exponential backoff (honouring
Retry-After), and additionally watches GitHub's primary rate-limit signal
(X-RateLimit-Remaining: 0 + X-RateLimit-Reset) to sleep until the limit
resets rather than blindly backing off — controlled by HTTP_MAX_RETRIES and
HTTP_TIMEOUT.
Install & run
cd github-mcp
python -m venv .venv && source .venv/bin/activate # .venv\Scripts\Activate.ps1 on Windows
pip install -e . # base install: mcp, httpx, uvicorn
pip install -e ".[java]" # + tree-sitter/tree-sitter-java for AST-accurate fragments
cp .env.example .env # fill in GITHUB_TOKEN
# stdio:
python -m github_mcp --transport stdio
# HTTP (streamable-http at http://127.0.0.1:8082/mcp):
python -m github_mcp --transport http
Register with an MCP client (stdio example)
{
"mcpServers": {
"github": {
"command": "python",
"args": ["-m", "github_mcp", "--transport", "stdio"],
"env": {
"GITHUB_TOKEN": "…",
"GITHUB_OWNER": "anands-bounteous",
"GITHUB_REPO": "nexpose"
}
}
}
}
Ports
This server's HTTP transport defaults to 8082 — jira-confluence-mcp uses
8080 and log-intelligence-mcp uses 8081, so all three can run simultaneously.
Tests
pytest # in an environment with pytest installed
python tests/_runner.py # offline harness when pytest isn't installed
Covers base-URL normalisation, content decoding, line-slicing, directory/repo/
branch/commit normalisation, search-query building and result normalisation,
and — via a stub HTTP transport (FakeClient, no network needed) — file
fetch with the MAX_FILE_KB size guard, directory listing, repo info/readme/
branches/commits, the search_code no-token guard, and the fragment-backend
factory. The Java regex backend is exercised directly against a realistic
fixture source file (tests/fixtures/Sample.java) covering nested classes, an
interface, a generic method, an annotated method, and a string literal
containing {/} to prove brace-in-string masking works. 30 tests, all
offline — none need GITHUB_TOKEN or network access.
If
tree-sitter-javaisn't installed, tests targetRegexJavaBackendexplicitly rather than relying onFRAGMENT_BACKEND=autoresolution, so the suite stays runnable regardless of what's pip-installed.
Live GitHub API calls (a real
search_code/get_file_contentsagainstanands-bounteous/nexpose) need a realGITHUB_TOKENand network access, which the automated test suite doesn't exercise — see "Install & run" above to try them manually.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。