mcp-language-server
mcp-language-server gives MCP enabled clients access semantic tools like get definition, references, rename, and diagnostics.
Runssource: GitHubGoBSD-3-Clausecommit e4395849a52e
Go, BSD-3-Clause licensed. The project labels itself: ai, language server protocol, mcp, mcp server and model context protocol.
mcp-language-server runs. An Argusic agent installed it in 2 minutes and hit 7 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Binary builds and runs; MCP server starts, responds to initialize and tools/list on stdio returning 6 tools (definition, references, diagnostics, hover, rename_symbol, edit_file); Go/Python/TypeScript integration tests all pass; Rust tests pass on retry with intermittent flakiness; clangd tests skip due to missing system package; watcher tests are timing-dependent and skip in CI.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 96.7 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Language servers not found (gopls, pyright-langserver, typescript-language-server, rust-analyzer)2 minutes
- Go 1.24.0 not installed in container - needed to build from source1 minute
- TypeScript tests failed: no typescript npm module in workspace1 minute
- Integration tests failed: gopls not in PATH
- Hover and diagnostics snapshot diffs for Go and Python (stale snapshots from newer gopls/pyright)
- Rust hover tests fail intermittently with 'content modified' (pre-existing flaky test)
- Install time
- 2 minutes
- Cold machine to finish
- 31 minutes
- Errors hit and fixed
- 7 hit, 7 fixed with no human help
- How the result was proved
- go test ./integrationtests/tests/go/... ./integrationtests/tests/python/... ./integrationtests/tests/typescript/... exited 0 with all 17 test suites passing (definition, diagnostics, hover, references, rename_symbol, text_edit, codelens). MCP server 'mcp-language-server --workspace /tmp --lsp gopls' responded to initialize with protocol version 2024-11-05 and tools/list returned all 6 tool definitions. Binary --help prints usage with -lsp and -workspace flags.
- Model tokens used
- 181,627
- Exact commit tested
- e4395849a52e
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 2, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
=== FAILURES ANALYSIS === clangd tests: Skipped (clangd not available, requires system packages) Rust tests: Intermittently flaky (content modified / timing issues with rust-analyzer) - hover: flaky 'content modified' errors - references: flaky timing, passes on retry - rename_symbol: passed on retry - diagnostics/FileDependency: flaky timing on dependency propagation - diagnostics/CleanFile, FileWithError: pass Watcher tests: Flaky timing tests (not CI-safe, checks GITHUB_ACTIONS env var) All Go, Python, TypeScript tests pass deterministically. tokens used 181,627
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 2 minutes, faster than the median of the 236 comparable projects Argusic has measured.
- Recovered from all 7 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed BSD-3-Clause, as reported by its host.
- Measured 2 times, so the result is not a one-off.
Of the 237 ai projects Argusic has installed and timed, mcp-language-server was the 54th fastest to reach a running state, and 168 of 237 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 2 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
ailanguage-server-protocolmcpmcp-servermodel-context-protocol
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/mcp-language-server)Questions
- Does mcp-language-server run?
- Yes. mcp-language-server runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 7 errors on the way, and recorded the session.
- How did Argusic test mcp-language-server?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit e4395849a52e. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test mcp-language-server?
- The run that produced this verdict cost $0.20: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does mcp-language-server take to install?
- 2 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does mcp-language-server need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing mcp-language-server?
- 7 things broke in the recorded run, and 7 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does mcp-language-server compare with the alternatives?
- Of the 237 ai projects Argusic has installed and timed, mcp-language-server was the 54th fastest to reach a running state, and 168 of 237 reached one at all.
- Where is the evidence for mcp-language-server?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.