LSP setup for GitHub Copilot CLI
Enable code intelligence in GitHub Copilot CLI — detect the OS, install the right language-server binary, and generate valid user- or repo-level JSON config for any language, with verification
- What
- Enable code intelligence in GitHub Copilot CLI — detect the OS, install the right language-server binary, and generate valid user- or repo-level JSON config for any language, with verification
- Cost
- Free
- Needs
- the GitHub Copilot CLI installed, plus a package manager (Homebrew, apt, winget, etc.) to fetch the LSP server binary — the skill is a setup utility the agent follows
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @github's utility skill for installing and configuring Language Server Protocol servers for the GitHub Copilot CLI. A 7-step workflow: ask which language (via `ask_user` with choices), detect the OS, look up the server and install command in `references/lsp-servers.md` (plus `references/java-jdtls.md` for Java), ask the config scope (user-level `~/.copilot/lsp-config.json` or repo-level `.github/lsp.json`), install the server binary, write and merge the JSON config (never clobber existing entries), and verify the binary is on `$PATH` with valid JSON — unlocking go-to-definition, find-references, hover and type info. Documents the `lspServers` config schema (`command`, `args --stdio`, `fileExtensions` mapping), restart semantics (`/exit` then relaunch, check with `/lsp`). Updated October 22, 2026: upstream corrected the repo-level config path — a bare `lsp.json` at the repo root is not read by Copilot CLI (verified on 1.0.95 with `copilot lsp list`); `.github/lsp.json` is the only repo-level location — and added a Java section (the jdtls reference; prefer the `lsp` tool over grep/view for Java semantic navigation once a server is configured). Honest caveats: utility only — needs the Copilot CLI installed and a package manager to fetch the server binary; unlisted languages require a manual web search for the right server. MIT licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
LSP setup for GitHub Copilot CLI is a free Muse skill installing and configuring Language Server Protocol servers for the GitHub Copilot CLI. Its 7-step workflow asks which language, detects the OS, looks up the server and install command, asks the config scope, user-level or repo-level, installs the server binary, and writes and merges the JSON config, with verification.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit 2d4b998Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: the GitHub Copilot CLI installed, plus a package manager (Homebrew, apt, winget, etc.) to fetch the LSP server binary — the skill is a setup utility the agent follows Install "LSP setup for GitHub Copilot CLI" for me. It gives my agent @github's LSP setup workflow: ask which language(s) need code intelligence, detect the OS, look up the server and install command in references/lsp-servers.md (for Java, also references/java-jdtls.md), ask the config scope (user-level ~/.copilot/lsp-config.json or repo-level .github/lsp.json), install the server binary, write and merge the JSON config without clobbering existing entries, and verify the binary is on $PATH with valid JSON — enabling go-to-definition, find-references, hover and type info. For Java, once a server is configured, prefer the lsp tool over grep/view for semantic navigation. Reminds the user to /exit and relaunch Copilot CLI so the config loads, then check with /lsp. MIT-licensed. Repository: https://raw.githubusercontent.com/github/awesome-copilot/2d4b998d2df28917074ee33db45c9601484c72ad/skills/lsp-setup/SKILL.md (the skill is the whole skills/lsp-setup/ folder at that commit: SKILL.md plus references/lsp-servers.md and references/java-jdtls.md) Pinned version: install the code at commit 2d4b998d2df28917074ee33db45c9601484c72ad exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. Updated October 22, 2026: Skill Harbor regenerated this install prompt from the current upstream file (SKILL.md, 3,981 → 4,320 characters). CORRECTION: the previous prompt presented a bare lsp.json at the repo root as a repo-level option, with a "keep an existing root location, or ask which repo-level location" choice. Upstream now states — verified against Copilot CLI 1.0.95, where `copilot lsp list` listed servers from .github/lsp.json but not from a root lsp.json — that a root lsp.json is not read at all: .github/lsp.json is the only repo-level location, and the root option and that choice are gone from this prompt. Also new upstream: step 3 sends Java setups to references/java-jdtls.md as well, and a new Java section says to prefer the lsp tool (goToDefinition, findReferences, hover, incomingCalls) over grep/view for Java semantic navigation once a server is configured — LSP stays optional for Java and is not a prerequisite for build or runtime diagnostics. 1. Fetch the whole skills/lsp-setup/ folder at the pinned commit (SKILL.md and both files under references/) into a temporary folder, then compare SKILL.md with the fingerprint from Skill Harbor's review of 2026-10-22: - SKILL.md: SHA-256 f905990ab13b4d234d87c274e12d9d9c01841706b17ed05902361ecfd3dbe0ee If it does not match, it changed since the review: do not install it yet, tell me what you found and let me decide. 2. Safety check: read SKILL.md and its reference files and review them for anything suspicious (unexpected network calls, shell commands, credential harvesting); STOP on any red flag and tell me. This repo should contain zero secrets in code — verify that holds here. Tell me in plain words what the skill does when used, and confirm these points from the files: - The skill is a setup utility — guidance plus reference tables, no executable code in the folder (SKILL.md and two Markdown references) — and nothing is sent anywhere during installation itself. In use, following it runs the package-manager install command for the chosen language's LSP server binary and writes or merges a JSON config file; that is the whole footprint. - There are exactly two config locations, and repo-level takes precedence over user-level: ~/.copilot/lsp-config.json and .github/lsp.json. A bare lsp.json at the repo root is NOT read (upstream verified this on Copilot CLI 1.0.95 with `copilot lsp list`). The config holds an lspServers map (command, args — almost always --stdio — and fileExtensions mapping each extension to a language ID); multiple servers coexist, and merging never overwrites other servers' entries — only the target language key is added or updated. The final config JSON is shown to the user before it is written. - The workflow asks before acting: ask_user with choices for the language(s) and for the scope. If a language is not listed in references/lsp-servers.md, it falls back to a web search for "<language> LSP server" and guides a manual configuration; if no package manager is available, it suggests alternative install methods from the reference file. - After setup, the user must /exit and relaunch Copilot CLI for the new configuration to load, then check the server with /lsp; the binary's presence on $PATH is verified (which, or where.exe on Windows). - For Java, references/java-jdtls.md carries the jdtls setup details and troubleshooting, and the skill says to prefer the lsp tool (goToDefinition, findReferences, hover, incomingCalls) over grep/view for Java semantic navigation once a server is configured; LSP is optional for Java and is not a prerequisite for build or runtime diagnostics. 3. When I say yes, install it as a skill: copy SKILL.md and its reference files into the agent's skills directory, in a folder named "lsp-setup", keeping the references/ subfolder structure as it is. 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. install the Copilot CLI, tell the agent which language to set up — the agent asks me before writing any config; and if I previously created a repo-root lsp.json, Copilot CLI ignores it — its entries belong in .github/lsp.json). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 2d4b998 · 2026-10-22
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-22 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.