mcp-server-development
Skill9 starsChanged 5 months agoMITView on GitHub
Implementation patterns for the ableton-mind TypeScript MCP server: Zod tools, resources, prompts, bridge client, verify loop, transactions and idempotency.
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill when implementing or reviewing src/server, src/tools, src/resources, src/prompts, src/live-client or src/feedback.
- Distinctive: line 26
Keep a persistent JSON-RPC TCP client with request IDs, timeout, reconnect backoff and notification events.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
MCP Server Development — TS/Node Patterns
Use this skill when implementing or reviewing src/server, src/tools, src/resources, src/prompts, src/live-client or src/feedback.
Stack
TypeScript 5, Node 20, ESM, @modelcontextprotocol/sdk, zod, tsup, biome, vitest and native net.
Tool Rules
- Tool names use snake_case and align with Python handler names.
- Descriptions explain what changes, idempotency and side effects.
- Input and output schemas use Zod. Avoid any and unknown except debug sinks.
- Handlers are async and receive input plus ctx.
- Mutations read before write and verify by reading back.
- Return ok, verified and diff where relevant.
- Errors are structured and never call process.exit.
Bridge Client
Keep a persistent JSON-RPC TCP client with request IDs, timeout, reconnect backoff and notification events. Tools talk through the context abstraction, not by importing low-level clients directly.
Resources and Prompts
Resources expose live state or embedded knowledge without mutating Live. Prompts are short client-visible templates and should not replace documentation.
Tests
Each tool needs at least one happy path and one validation/error path. Integration tests use a mock bridge by default and a real bridge only when explicitly enabled.
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- Hack23/European-Parliament-MCP-Server★ 30same name
- Indium-AI-Labs/indium-agentkit★ 18same name
- Ionate-Technologies/indium-agentkit★ 17same name
- asmamest/Nexus-Skills★ 1same name
- KMaruthi2002/universal-llm-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ableton-mind-buildSkill
- ableton-remote-scriptSkill
- cross-boundary-qaSkill
- device-schema-extractionSkill
- mcp-distributionSkill
- recipe-authoringSkill
- ableton-mind-buildSkill
- ableton-mind-quality-auditSkill
- ableton-remote-scriptSkill
- command-surface-auditSkill
- cross-boundary-qaSkill
- device-schema-extractionSkill
- local-copilotSkill
- mcp-distributionSkill
- mcp-server-developmentSkill
- recipe-authoringSkill
- refactor-maintainabilitySkill
- runtime-release-auditSkill
- security-auditSkill
- test-coverage-expansionSkill
- usability-flow-auditSkill
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.