Coding Tools MCP
Provides Git repository tools for inspecting status, diffs, commit history, file details, and blame information.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Coding Tools MCP run the test suite and fix the first failure"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Coding Tools MCP
English | 简体中文
Give any AI chat or agent a safe pair of hands on your codebase.
Coding Tools MCP is a model-neutral coding runtime served over the Model Context Protocol: file reading and search, structured multi-file patches, command execution, interactive sessions, and git — one server that any MCP client can drive. Claude Desktop, Claude Code, Cursor, Cline, or an agent you build yourself all get the same 20 battle-tested tools, confined to one workspace, gated by permission modes.

Why people use it
It turns a chat app into a coding agent. Claude Desktop — or any MCP chat client — gets real repo access with the subscription you already have. No extra product required.
Safety is the product, not an afterthought. One workspace root per server. Absolute paths,
..traversal, and symlink escapes are rejected. Permission modes gate network access, shell expansion, inline scripts, and destructive commands. On Linux, Landlock adds kernel-level filesystem confinement.It is model- and vendor-neutral. A fixed, truthfully annotated catalog — no profile switching, no annotation games. Swap models or clients freely; the runtime and its behavior stay put.
It is engineered for context windows. Results are summarized, paginated, and capped by design; serialized tool-result bytes dropped 37% release-over-release on the deterministic dogfood workload with unchanged task completion.
Related MCP server: Cloud Harness MCP
Quickstart
Run it with whichever toolchain you already have (the server is Python ≥ 3.11
from PyPI; the npm package is a thin launcher that starts it via uv or
pipx):
uvx coding-tools-mcp --stdio --workspace /path/to/repo # Python toolchain
npx coding-tools-mcp --stdio --workspace /path/to/repo # Node toolchainWire it into Claude Desktop, Claude Code, Cursor, or Cline — the JSON is the
same everywhere (swap uvx for npx if you prefer Node):
{
"mcpServers": {
"coding-tools": {
"command": "uvx",
"args": ["coding-tools-mcp", "--stdio", "--workspace", "/path/to/repo"]
}
}
}Then ask your client: "run the test suite and fix the first failure."
Prefer HTTP? Drop --stdio and the server speaks Streamable HTTP on
http://127.0.0.1:8765/mcp (MCP 2025-11-25, with 2025-06-18
compatibility). A one-line installer, per-client walkthroughs, and
troubleshooting live in docs/quickstart.md and
docs/mcp-client-config.md.
Seven things to try
1. Make Claude Desktop your coding agent. The config above is all it takes — the chat window you already pay for can now read, patch, test, and commit-review a real repository.
2. Code on your own machine from anywhere.
CODING_TOOLS_MCP_AUTH_MODE=bearer ./scripts/tunnel.sh cloudflared /path/to/repoLoopback bind + authenticated HTTPS tunnel (cloudflared, ngrok, or
Microsoft Dev Tunnel). Point claude.ai on your phone at
https://<tunnel-host>/mcp and drive your home workstation from anywhere.
Bearer tokens and OAuth 2.1 + PKCE (with RFC 7591 dynamic registration) are
built in. → docs/remote-mcp.md
3. Let an agent loose on untrusted code — inside a disposable sandbox.
docker build -t coding-tools-mcp-sandbox:local .
docker run --rm --init -it -p 8765:8765 -v "$PWD:/workspace" coding-tools-mcp-sandbox:localA containerized server with toolchains and caches preconfigured, safe to point at a sketchy PR and destroy afterwards. → docs/docker.md
4. Spin up a cloud sandbox with one MCP call. The bundled
Cloudflare Worker control plane exposes
start_coding_tools_sandbox as an MCP tool: one call dispatches a GitHub
Actions runner that boots the Docker sandbox and publishes it behind an
authenticated Cloudflare Tunnel. Ephemeral compute, no server of your own.
5. Drive it from a GUI.
python -m pip install "coding-tools-mcp[desktop]"
coding-tools-mcp-desktopPer-workspace profiles, server and tunnel start/stop, credential setup with clipboard helpers, live health checks. English and 简体中文.
6. Keep an interactive session alive. exec_command starts a REPL or
debugger under a real PTY; write_stdin feeds it across turns; read_output
pages long output; kill_session cleans up. Long-running processes are
first-class, with deadline watchdogs and bounded buffers.
7. Give your own agent production-grade hands. Building an agent loop with the Anthropic SDK or anything else? Don't hand-roll file and exec tools — speak MCP to this server and inherit the whole safety boundary. → docs/embedding.md
The tool catalog
One stable, truthfully annotated set — permission modes change command
policy, never which tools the model sees. apply_patch is the sole
file-mutation primitive: staged, baseline-checked, atomic across files, with
rollback.
Group | Tools |
Files & search |
|
Execution |
|
Git |
|
Runtime |
|
Root AGENTS.md/CLAUDE.md files load into the initialize context
automatically. Tool content is concise agent-facing text;
structuredContent carries the complete machine result. Schemas and result
envelopes: docs/tools-and-schemas.md ·
docs/runtime-contract-v0.2.md.
Safety Boundary
Mode | Meant for | What it allows |
| day-to-day agent work | file tools and vetted commands; network-looking commands, shell expansion, inline scripts, and destructive commands all require explicit permission |
| local development | opens network, shell expansion, and inline scripts; keeps secret filtering and destructive-command checks |
| isolated containers/VMs only | disables |
Recursive listing and search exclude .git, node_modules, build outputs,
virtualenvs, and caches. Commands run with workspace-bound cwd, scrubbed
environment, timeouts, and output caps. Linux hosts with Landlock get
kernel-enforced filesystem confinement; other platforms get an explicit
warning — this is still not a complete OS sandbox, so use the Docker image or
a VM for genuinely untrusted work. Details:
SECURITY.md · docs/security-boundary.md ·
docs/permission-modes.md
Telemetry
The server sends anonymous usage telemetry (per-tool success/latency counters
and version/platform dimensions — never paths, arguments, commands, or file
contents) to help prioritize fixes. Disable it with
CODING_TOOLS_MCP_TELEMETRY=off or DO_NOT_TRACK=1; it is automatically off
in CI. CODING_TOOLS_MCP_TELEMETRY=debug prints every event to stderr instead
of sending. The full event list and guarantees are in
docs/telemetry.md.
Evidence, Dogfood and SWE-bench
Every release ships through a tag-triggered pipeline in which the compliance
suite, real-workload benchmark, and SWE-bench harness run from the same commit
that publishes to PyPI and npm — both via trusted publishing, npm with
provenance. Dogfood efficiency metrics are reproducible (make dogfood-smoke)
and checked in under reports/. This repository does not claim a
model-generated SWE-bench leaderboard result — see
docs/swe-bench.md for exactly what is and is not
measured. More: COMPLIANCE.md · BENCHMARK.md ·
docs/dogfood.md
Documentation
Getting started | |
Remote & sandboxed | |
Tools & contract | |
Execution | |
Integration | |
Security & quality | Security policy · Security boundary · CI and tests · Limitations · Competitive analysis |
Development
python -m pip install -e ".[dev]"
make ci # lint, typecheck, tests, protocol/integration suites, gatesThe full gate matrix is in docs/ci-and-tests.md.
License
This project is licensed under the Apache License 2.0.
If you use code, documentation, substantial implementation details, or derivative work from this project, preserve the copyright notice, license notice, and NOTICE file, and clearly attribute the original project.
Project: Coding Tools MCP
Author: Coding Tools MCP Contributors
Source: https://github.com/xyTom/coding-tools-mcp
Citation metadata is available in CITATION.cff.
Available Tools
18 toolsapply_patchApply patchADestructive
Stage, validate, and atomically apply a patch envelope. Example: *** Begin Patch *** Update File: app.py @@ -old +new *** End Patch
Inputs: patch (required), dry_run. Returns: ok, error
check_exec_environmentCheck exec environmentARead-onlyIdempotent
Return lightweight exec_command sandbox and environment status known to the server.
Inputs: no named parameters. Returns: ok, error
exec_commandExecute commandADestructive
Run a bounded command under runtime policy. Pass workdir explicitly for reconnect-safe paths. A still-running command returns command_id. Example: {"cmd":"pytest -q","workdir":".","yield_time_ms":30000}. Retained output is bounded per stream; for very large output redirect to a file (cmd > out.log 2>&1) and page it with read_file or search_text.
Inputs: cmd (required), cwd, env, tty, +7 more. Returns: ok, error
git_blameGit blameARead-onlyIdempotent
Return bounded git blame metadata for a workspace file.
Inputs: path (required), rev, end_line, max_lines, +1 more. Returns: ok, error
git_diffGit diffCRead-onlyIdempotent
Return unified git diff for workspace changes.
Inputs: path, paths, staged, unstaged, +2 more. Returns: ok, error
git_logGit logBRead-onlyIdempotent
Return recent git commits with bounded structured metadata.
Inputs: ref, path, skip, max_count. Returns: ok, error
git_showGit showBRead-onlyIdempotent
Return bounded git show output for a revision.
Inputs: rev, path, paths, max_bytes, +2 more. Returns: ok, error
git_statusGit statusBRead-onlyIdempotent
Return git working tree status for the workspace.
Inputs: path, max_entries, include_untracked. Returns: ok, error
kill_commandKill commandBDestructive
Terminate a server-managed command by command_id. Example: {"command_id":"abc","signal":"KILL"}.
Inputs: command_id (required), signal, wait_ms, verbosity, +3 more. Returns: ok, error
list_dirList directoryCRead-onlyIdempotent
List directory entries inside the configured workspace.
Inputs: path, sort, max_depth, recursive, +3 more. Returns: ok, error
list_filesList filesBRead-onlyIdempotent
List workspace files using glob filters.
Inputs: glob, path, sort, patterns, +4 more. Returns: ok, error
read_fileRead fileBRead-onlyIdempotent
Read a UTF-8 text file slice inside the configured workspace.
Inputs: path (required), encoding, end_line, max_bytes, +2 more. Returns: ok, error
read_outputRead outputARead-onlyIdempotent
Read retained command output using an output_ref returned by exec_command/write_stdin. Each stream retains the earliest output (head) plus the most recent output (rolling tail); bytes between them may be evicted and are reported via evicted_gap_bytes. Example: {"output_ref":"command:abc:stdout","offset":0,"limit":4096}.
Inputs: output_ref (required), limit, offset, stream. Returns: ok, error
request_permissionsRequest permissionsARead-only
Report scoped permission-request status without silently granting operations.
Inputs: reason (required), arguments (required), tool_name (required), permission (required), +2 more. Returns: ok, error
search_textSearch textBRead-onlyIdempotent
Search UTF-8 workspace files for text or regex matches.
Inputs: query (required), glob, path, regex, +6 more. Returns: ok, error
server_infoServer infoARead-onlyIdempotent
Return server, workspace, project-context, auth, policy, and fixed-tool metadata.
Inputs: no named parameters. Returns: ok, error
view_imageView imageCRead-onlyIdempotent
Return a workspace image as MCP image content.
Inputs: path (required), max_bytes, max_width, max_height, +1 more. Returns: ok, error
write_stdinWrite stdinB
Poll or interact with a running command by command_id. Empty chars wait for output; non-empty chars writes to stdin. Example: {"command_id":"abc","chars":"","yield_time_ms":10000}.
Inputs: command_id (required), chars, verbosity, preview_bytes, +2 more. Returns: ok, error
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 18 tools
Most tools target a distinct action or resource, and the descriptions clarify their roles. Minor overlap exists between list_dir and list_files for workspace browsing, and server_info and check_exec_environment both report environment metadata, but an agent can generally disambiguate them.
The naming is largely consistent with snake_case verb_noun patterns like read_file, apply_patch, and kill_command, plus a coherent git_* prefix group. A few names like server_info and check_exec_environment are more noun-like or verbose, but the overall pattern is predictable.
Eighteen tools is slightly above the typical well-scoped range, but each tool serves a plausible purpose for a coding workspace server: file inspection, patching, command execution, git inspection, and permissions. It is not bloated enough to feel overwhelming or redundant.
The server covers core coding workflows well: reading and searching files, applying patches, running and interacting with commands, and inspecting git history. Some operations like explicit file creation/deletion or git writing operations are not first-class tools, but exec_command and apply_patch provide workarounds, so the gaps are minor.
Related MCP Connectors
One MCP server for all your MCP servers: code mode, per-tool permissions, approvals and audit.
A MCP server built for developers enabling Git based project management with project and personal…
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
An MCP server that gives your AI access to the source code and docs of all public github repos
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceExposes a secure, path-confined bridge to a local workspace and git remotes, enabling MCP clients to search, read, write, reset files, and perform git operations.-
- AlicenseNot gradedqualityBmaintenanceEnables AI clients to securely operate isolated coding workspaces with file, command, Git, and deployment tools via authenticated remote MCP.108MIT
- AlicenseNot gradedqualityCmaintenanceGives any MCP-compatible AI chat or agent a safe, model-neutral coding runtime with file read/search, structured multi-file patches, command execution, interactive sessions, and git operations, all confined to a single workspace and gated by permission modes.Apache 2.0
- AlicenseNot gradedqualityBmaintenanceGives MCP-compatible AI clients safe, hands-on access to local codebases: file reading/search, multi-file patches, command execution, interactive sessions, Git inspection, and coordination of local agent providers such as Antigravity and OpenCode.18Apache 2.0