agent-lsp

MCP server for language intelligence. Give AI agents structured access to language servers: go-to-definition, find-all-references, rename, diagnostics, completions, call hierarchy, and speculative execution.

66 tools. 23 agent workflows. 30 CI-verified languages. Single Go binary.

Why

AI coding agents navigate code with grep and file reads. This wastes 5-34x more tokens than necessary and produces 92-99% false positives on symbol lookups. Language servers already have the answers; agent-lsp makes them accessible via MCP.

Install

pip install agent-lsp

Or via other channels:

brew install blackwell-systems/tap/agent-lsp    # macOS/Linux
npm install -g @blackwell-systems/agent-lsp     # npm
curl -fsSL https://raw.githubusercontent.com/blackwell-systems/agent-lsp/main/install.sh | sh

Usage

# Start with auto-detection
agent-lsp

# Explicit language server
agent-lsp go:gopls typescript:typescript-language-server,--stdio

# HTTP mode
agent-lsp --http --port 8080 go:gopls

Then configure your AI tool's MCP settings to point at agent-lsp.

What it does

66 tools covering navigation, analysis, refactoring, diagnostics, formatting, speculative execution, composite exploration, safe editing, build, test, and more
23 agent workflows (skills) that encode correct multi-step operations: rename safely, analyze blast radius, simulate edits before applying
30 CI-verified languages: Go, Python, TypeScript, Rust, Java, C, C++, C#, Ruby, PHP, Kotlin, Swift, Scala, Zig, Lua, Elixir, Gleam, and more
Speculative execution: preview edits in memory, see what breaks before touching disk
Phase enforcement: blocks out-of-order operations so agents follow correct workflows

Token savings

Measured across 5 codebases (Go, TypeScript, Python):

Codebase	Lines	Savings
agent-lsp	15K	5x
Hono (TypeScript)	24K	13x
FastAPI (Python)	33K	2x
Next.js (TypeScript)	196K	5x
HashiCorp Consul (Go)	319K	34x

Full experiment: agent-lsp.com/token-savings

Works with

Claude Code, Cursor, Windsurf, GitHub Copilot, and any MCP-compatible client.

Metadata

Release files for agent-lsp 0.23.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distributions (wheels)

Table of built distributions (wheels) for agent-lsp 0.23.0
File	Interpreter	ABI	Platform	Reset
agent_lsp-0.23.0-py3-none-win_arm64.whl 10.9 MB Oct 8, 2026	Python 3	none	Windows ARM64	Details
agent_lsp-0.23.0-py3-none-win_amd64.whl 6.1 MB Oct 8, 2026	Python 3	none	Windows x86-64	Details
agent_lsp-0.23.0-py3-none-manylinux2014_x86_64.whl 12.1 MB Oct 8, 2026	Python 3	none	Linux glibc 2.17+ x86-64	Details
agent_lsp-0.23.0-py3-none-manylinux2014_aarch64.whl 11.5 MB Oct 8, 2026	Python 3	none	Linux glibc 2.17+ ARM64	Details
agent_lsp-0.23.0-py3-none-macosx_11_0_arm64.whl 11.7 MB Oct 8, 2026	Python 3	none	macOS 11.0+ ARM64	Details
agent_lsp-0.23.0-py3-none-macosx_10_12_x86_64.whl 12.2 MB Oct 8, 2026	Python 3	none	macOS 10.12+ x86-64	Details

Total release size: 64.5 MB

Release files / agent_lsp-0.23.0-py3-none-win_arm64.whl

Download URL	agent_lsp-0.23.0-py3-none-win_arm64.whl
Size	10.9 MB
Tags	Python 3 Windows ARM64
SHA-256 checksum How to use checksums	`1a3dcad5301bdf150e6fefbfb33761cd20d02e84b1650a3d9ca6a436b7913185`
BLAKE2b-256 checksum How to use checksums	`9d25eb62dd860625128c438d7d55c2e8b87c2848bc98ce1e8a635696702bd581`
Upload date	Oct 8, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.12.14`

Release files / agent_lsp-0.23.0-py3-none-win_amd64.whl

Download URL	agent_lsp-0.23.0-py3-none-win_amd64.whl
Size	6.1 MB
Tags	Python 3 Windows x86-64
SHA-256 checksum How to use checksums	`02be1d888cb122048618d122b198beb88d47a1d5be38b31a15a49507c5e18827`
BLAKE2b-256 checksum How to use checksums	`b4587722625f3c86f42ce9ff29a74a1278821ab74820bf90ab6cf9a43aa51388`
Upload date	Oct 8, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.12.14`

Release files / agent_lsp-0.23.0-py3-none-manylinux2014_x86_64.whl

Download URL	agent_lsp-0.23.0-py3-none-manylinux2014_x86_64.whl
Size	12.1 MB
Tags	Linux glibc 2.17+ x86-64 Python 3
SHA-256 checksum How to use checksums	`879b29f9ed3d8874274bcbf177ce332c86f56caf4330c75e34ec3a2064346795`
BLAKE2b-256 checksum How to use checksums	`07be23301e1493e13a3258f24bb63a40406fbf4b5029005a00417f46da767b16`
Upload date	Oct 8, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.12.14`

Release files / agent_lsp-0.23.0-py3-none-manylinux2014_aarch64.whl

Download URL	agent_lsp-0.23.0-py3-none-manylinux2014_aarch64.whl
Size	11.5 MB
Tags	Linux glibc 2.17+ ARM64 Python 3
SHA-256 checksum How to use checksums	`e356d3eb3babf188db8400f7f68d04bc92ad43d3b9eeb74ca0d740ee9f5c5fa0`
BLAKE2b-256 checksum How to use checksums	`86680b51ebfd53d911439151e4967ca307e960b5e1bac0ed54653ecdfe39d5e6`
Upload date	Oct 8, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.12.14`

Release files / agent_lsp-0.23.0-py3-none-macosx_11_0_arm64.whl

Download URL	agent_lsp-0.23.0-py3-none-macosx_11_0_arm64.whl
Size	11.7 MB
Tags	Python 3 macOS 11.0+ ARM64
SHA-256 checksum How to use checksums	`907686bd2f81e092ed3ac5d543fab6cfdd99aa67527b8e56b0e2f105ecb7b223`
BLAKE2b-256 checksum How to use checksums	`24d403880cba8f393013c4e5bfdb5de509af9613f710343912d0a87f9dc8f4e5`
Upload date	Oct 8, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.12.14`

Release files / agent_lsp-0.23.0-py3-none-macosx_10_12_x86_64.whl

Download URL	agent_lsp-0.23.0-py3-none-macosx_10_12_x86_64.whl
Size	12.2 MB
Tags	Python 3 macOS 10.12+ x86-64
SHA-256 checksum How to use checksums	`04ff891819211942828e3acaff33178e4678207b8e636f8db3ba98febfcd5a47`
BLAKE2b-256 checksum How to use checksums	`e2b7f93c2e8ed113050f6b810763e7973165c2b9706350ca5d8aa10748b3cd2c`
Upload date	Oct 8, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.12.14`