mcp-discovery
Skill5 starsChanged 18 days agoMITView on GitHub
Find and start a zero-environment local MCP server when the session lacks a capability that no available tool, project script, or ordinary local code can cover.
In this repository46 other files it gives its agents.
- batchSkill
- best-of-nSkill
- datavizSkill
- debugSkill
- delegateSkill
- dependency-updateSkill
- documentSkill
- documentsSkill
- docxSkill
- fleet-managerSkill
- flightsSkill
- forgetSkill
- frontend-designSkill
- githubSkill
- gmailSkill
- goalsSkill
- google-calendarSkill
- handoffSkill
- helpSkill
- image-searchSkill
- implementSkill
- interviewSkill
- mcp-builderSkill
- moneySkill
- pdfSkill
- photosSkill
- planSkill
- plugin-creatorSkill
- podcastSkill
- pptxSkill
- presentationsSkill
- releaseSkill
- researchSkill
- reviewSkill
- security-reviewSkill
- shoppingSkill
- simplifySkill
- skill-creatorSkill
- skill-installerSkill
- spotifySkill
- spreadsheetsSkill
- testSkill
- ttsSkill
- verifySkill
- webapp-testingSkill
- xlsxSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 47
Install + run transactionally: Call start_registry_mcp_server {registry_name: "<exact name>", arguments: {...}}.
- Distinctive: line 66
Don't attempt to pass env vars or secrets.
- Distinctive: line 67
Don't reconstruct or edit the Registry-provided package command.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
mcp-discovery
The public MCP Registry ships hundreds of ready-made stdio servers (filesystems, databases, browsers, media processing, developer utilities, cloud APIs, SaaS integrations, …). This skill is how you reach one when the session is genuinely missing a capability.
It is a fallback, not a first step. Discovery costs a tool_search to load the
deferred tools, a query, an approval, and an install — spend that only when it
buys a capability you do not have.
When to use
- An available tool, a project script or test, or a few lines of local code cannot do the job.
- The task needs an external service, database, or protocol client that this session has no access to.
- You would otherwise install a package or reimplement a well-known converter or client by hand.
When not to use
- Ordinary work: writing and editing files, reading fixtures, running repo commands, and checking your own output. Do those directly.
- A capability an already-loaded tool covers, even partially — try it first.
- A near-miss row in a result list. A scored match is a suggestion; the missing capability is what decides.
Workflow
- Name the gap. State the capability you lack before searching. If you cannot name one, you do not need the Registry.
- Load and query.
registry_syncandstart_registry_mcp_serverare deferred: load one withtool_searchand use the returned schema. If a call only loads the schema without executing, retry once with that schema. Then callregistry_sync {query: "<the missing capability>"}. It scores a host-side snapshot and returns at most eight matches; the full index never enters the conversation. Packages declaring any environment variable (including API keys/tokens) are excluded and never written to the cache. - Judge the matches. Take a server when it covers the gap you named. If nothing does, refine the query once, then continue with local tools.
- Install + run transactionally. Call
start_registry_mcp_server {registry_name: "<exact name>", arguments: {...}}. Supply only values listed inrequired_args; omitargumentswhen none are required. Never install or launch the package through the shell. Starting a server requires approval. - Solve the task with the new tools. Their complete schemas are added to the current turn immediately after a successful connection; call the exact names returned by the start result.
If a server fails to start
start_registry_mcp_server reports when a package exits before the handshake
(often CLI help output = incomplete launch args). Verify the exact required
arguments, retry once with the corrected structured values, and if it still
fails move on to the next candidate or to a local approach. Failed starts are
rolled back, so retrying the same Registry name is safe.
Don't
- Don't attempt to pass env vars or secrets; this flow has no env channel.
- Don't reconstruct or edit the Registry-provided package command.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

