mcp-server-selection
Skill0 starsChanged 15 days agoMITView on GitHub
Choose MCP servers from this repository's researched catalog using task fit, upstream status, permissions, and deployment constraints.
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 12
Read catalog/servers.json from the cloned repository.
- Distinctive: line 16
Prefer the narrowest scopes and resource access that accomplish the task.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Select an MCP server
Author: Sandeep Belgavi
Read catalog/servers.json from the cloned repository. Its ranking is only within a curated selection; stars measure repository attention, not security or compatibility. Suite entries represent multiple servers.
Match the user's concrete task to a small shortlist. For each candidate, open its linked upstream README and inspect the current installation, transport, authentication requirements, license, and write-capable tools. Report whether you checked documentation or actually executed the server. Do not copy another project's commands or infer package names from repository names.
Prefer the narrowest scopes and resource access that accomplish the task. For a database, distinguish schema inspection from arbitrary queries and mutations. For browser, filesystem, messaging and infrastructure servers, explain the relevant effect boundary. The catalog itself never authorizes installing packages or connecting accounts.
Return source links, fit, limitations, and the next concrete verification step. If upstream evidence conflicts with the snapshot, use current evidence and flag the stale record. Refresh the catalog with python scripts/refresh_catalog.py only when updating this repository is requested; it performs read-only GitHub checks and fails without overwriting the catalog if checks fail.
In this repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- cassandra-readonly-setupSkill
- mcp-contract-testingSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.