Skip to main content
Glama

Coding Tools MCP

English | 简体中文

Give any AI chat or agent a safe pair of hands on your codebase.

PyPI npm Python compliance release License

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.

Watch the demo

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 toolchain

Wire 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/repo

Loopback 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:local

A 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-desktop

Per-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

read_file · list_dir · list_files · search_text · apply_patch · view_image

Execution

exec_command · write_stdin · read_output · kill_session · request_permissions

Git

git_status · git_diff · git_log · git_show · git_blame

Runtime

server_info · check_exec_environment · get_default_cwd · set_default_cwd

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

safe (default)

day-to-day agent work

file tools and vetted commands; network-looking commands, shell expansion, inline scripts, and destructive commands all require explicit permission

trusted

local development

opens network, shell expansion, and inline scripts; keeps secret filtering and destructive-command checks

dangerous

isolated containers/VMs only

disables exec_command permission gates; workspace path boundaries still apply

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

Development

python -m pip install -e ".[dev]"
make ci        # lint, typecheck, tests, protocol/integration suites, gates

The 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 tools
apply_patchApply patchA
Destructive

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 environmentA
Read-onlyIdempotent

Return lightweight exec_command sandbox and environment status known to the server.

Inputs: no named parameters. Returns: ok, error

exec_commandExecute commandA
Destructive

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 blameA
Read-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 diffC
Read-onlyIdempotent

Return unified git diff for workspace changes.

Inputs: path, paths, staged, unstaged, +2 more. Returns: ok, error

git_logGit logB
Read-onlyIdempotent

Return recent git commits with bounded structured metadata.

Inputs: ref, path, skip, max_count. Returns: ok, error

git_showGit showB
Read-onlyIdempotent

Return bounded git show output for a revision.

Inputs: rev, path, paths, max_bytes, +2 more. Returns: ok, error

git_statusGit statusB
Read-onlyIdempotent

Return git working tree status for the workspace.

Inputs: path, max_entries, include_untracked. Returns: ok, error

kill_commandKill commandB
Destructive

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 directoryC
Read-onlyIdempotent

List directory entries inside the configured workspace.

Inputs: path, sort, max_depth, recursive, +3 more. Returns: ok, error

list_filesList filesB
Read-onlyIdempotent

List workspace files using glob filters.

Inputs: glob, path, sort, patterns, +4 more. Returns: ok, error

read_fileRead fileB
Read-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 outputA
Read-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 permissionsA
Read-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 textB
Read-onlyIdempotent

Search UTF-8 workspace files for text or regex matches.

Inputs: query (required), glob, path, regex, +6 more. Returns: ok, error

server_infoServer infoA
Read-onlyIdempotent

Return server, workspace, project-context, auth, policy, and fixed-tool metadata.

Inputs: no named parameters. Returns: ok, error

view_imageView imageC
Read-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

    B3.4/5.0

    Scored across 18 tools

    Disambiguation4/5

    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.

    Naming Consistency4/5

    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.

    Tool Count4/5

    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.

    Completeness4/5

    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

    Related MCP Servers

    • F
      license
      Not graded
      quality
      C
      maintenance
      Exposes 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.
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Gives 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
    • A
      license
      Not graded
      quality
      B
      maintenance
      Gives 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.
      18
      Apache 2.0