Skip to main content

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.

Links

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

agent_lsp-0.19.2-py3-none-win_arm64.whl (10.8 MB view details)

Uploaded Python 3Windows ARM64

agent_lsp-0.19.2-py3-none-win_amd64.whl (6.0 MB view details)

Uploaded Python 3Windows x86-64

agent_lsp-0.19.2-py3-none-manylinux2014_x86_64.whl (12.0 MB view details)

Uploaded Python 3

agent_lsp-0.19.2-py3-none-manylinux2014_aarch64.whl (11.4 MB view details)

Uploaded Python 3

agent_lsp-0.19.2-py3-none-macosx_11_0_arm64.whl (11.7 MB view details)

Uploaded Python 3macOS 11.0+ ARM64

agent_lsp-0.19.2-py3-none-macosx_10_12_x86_64.whl (12.1 MB view details)

Uploaded Python 3macOS 10.12+ x86-64

File details

Details for the file agent_lsp-0.19.2-py3-none-win_arm64.whl.

File metadata

  • Download URL: agent_lsp-0.19.2-py3-none-win_arm64.whl
  • Upload date:
  • Size: 10.8 MB
  • Tags: Python 3, Windows ARM64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.12.14

File hashes

Hashes for agent_lsp-0.19.2-py3-none-win_arm64.whl
Algorithm Hash digest
SHA256 7f29de3b2266a0056ba71de0c63a7ce27003780ec3b3a8cf7f63c488617620b0
MD5 70c867f2c1c0455686488cf8b13db9c6
BLAKE2b-256 12080f0a36d7dd9d8b324616ca150487e9ee2ceeeca9a7f133ce1c79c0057d73

See more details on using hashes here.

File details

Details for the file agent_lsp-0.19.2-py3-none-win_amd64.whl.

File metadata

  • Download URL: agent_lsp-0.19.2-py3-none-win_amd64.whl
  • Upload date:
  • Size: 6.0 MB
  • Tags: Python 3, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.12.14

File hashes

Hashes for agent_lsp-0.19.2-py3-none-win_amd64.whl
Algorithm Hash digest
SHA256 640eb0ecac57f4bbcaa3c1dbb9e6abd2d20d2567d41b9be86f5bcbef0cfad931
MD5 ec9f584723457c6cabf39bf2a05deb12
BLAKE2b-256 22adf7e4875e8bb06a07ebf5d06966a0b76f218d116f7036c1c040bf8e548d5d

See more details on using hashes here.

File details

Details for the file agent_lsp-0.19.2-py3-none-manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for agent_lsp-0.19.2-py3-none-manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 9ba44ad9f25bc2d79cb2c6b77feeff3791dad444ac3288a8c9a8c7b435c6d713
MD5 a52406fc09583bbe283d10c06a9034b0
BLAKE2b-256 70447c3323482ef03c3bd14c5ff75b06eb306e5a7fed708951baf009f62d0a59

See more details on using hashes here.

File details

Details for the file agent_lsp-0.19.2-py3-none-manylinux2014_aarch64.whl.

File metadata

File hashes

Hashes for agent_lsp-0.19.2-py3-none-manylinux2014_aarch64.whl
Algorithm Hash digest
SHA256 ea45a10a15b9f324d911a03ab2e164ab7ed281b572f7dabc8efeb8e4591fd581
MD5 8647746a0c2b3995eb149cb7c764ab31
BLAKE2b-256 3c4c845bc7362ce1b1a2d4baba0e2c0da78d294938c29c465f996050070283ff

See more details on using hashes here.

File details

Details for the file agent_lsp-0.19.2-py3-none-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for agent_lsp-0.19.2-py3-none-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 86578c426414511d35d5c4202f333606d4b5e90383432739c57307d8329510f0
MD5 30c12a99185bfe41a3278794e2433640
BLAKE2b-256 b66e269c3a5c53660963a5bdcc2b8f3dae3fbc1455babdb734f64b777e46f23c

See more details on using hashes here.

File details

Details for the file agent_lsp-0.19.2-py3-none-macosx_10_12_x86_64.whl.

File metadata

File hashes

Hashes for agent_lsp-0.19.2-py3-none-macosx_10_12_x86_64.whl
Algorithm Hash digest
SHA256 b7683bc84b03565030b35bb1f796a4295b99360a9078fab2ad427729ef0bb5c1
MD5 d518aa4b475b4267f19839a70aa8f1f2
BLAKE2b-256 c3dc59306c5a34d6b2ac87b152ff42aca33392736a081ea8a22d7d1b144f5ef5

See more details on using hashes here.

Release history Release notifications | RSS feed

This release

0.19.2 This release

6 files

0.19.1

6 files

0.19.0

6 files

0.18.0

6 files

0.17.0

6 files

0.16.0

6 files

0.15.2

6 files

0.15.1

6 files

0.15.0

6 files

0.14.0

6 files

0.13.0

6 files

0.12.0

6 files

0.11.2

6 files

0.11.1

6 files

0.11.0

6 files

0.10.0

6 files

0.9.0

6 files

0.8.1

6 files

0.8.0

6 files

0.7.0

6 files

0.5.4

6 files

0.5.3

6 files

0.5.2

6 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page