mcp-server-development
Skill1 starsChanged 17 days agoMITView on GitHub
Design, implement, and review Model Context Protocol servers exposing tools, resources, or prompts with clear schemas, least privilege, safe transport, and robust error handling.
We split this skill into the rules it gives an agent
10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
10
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 13
Write clear names and descriptions, typed input schemas, bounded outputs, and explicit error behavior.
- Distinctive: line 14
Keep tool implementations small and validate all arguments server-side.
- Distinctive: line 18
Treat tool results, resource contents, and prompt arguments as untrusted.
- Distinctive: line 19
Add timeouts, cancellation, bounded output, rate limiting, and safe logging.
- Distinctive: line 20
Test malformed messages, unknown methods, invalid arguments, unauthorized requests, oversized output, dependency failures, and repeated …
- Distinctive: line 21
Document installation, configuration, required permissions, data handling, supported protocol/client versions, and operational limitations.
- Distinctive: line 24
Use read-only tools by default where they meet the task.
- Distinctive: line 27
Use idempotency for writes that clients may retry.
- Distinctive: line 29
Never treat a tool description as an authorization boundary.
- Distinctive: line 32
Check path traversal, command injection, SSRF, secret leakage, overly broad OAuth scopes, token audience/issuer validation, confused-deputy …
“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
Goal
Build an MCP server that exposes a narrow, documented capability surface to compatible clients. MCP standardizes context/tool exchange; it does not automatically make a server or its tools safe.
Workflow
- Define the use case and choose tools, resources, and prompts deliberately. Do not expose capabilities that clients do not need.
- Write clear names and descriptions, typed input schemas, bounded outputs, and explicit error behavior.
- Keep tool implementations small and validate all arguments server-side.
- Enforce authentication and authorization for every protected resource/action. Derive identity from trusted credentials, not model-generated arguments.
- Apply least privilege to filesystem paths, databases, APIs, network access, and credentials.
- Select transport and authentication appropriate to the deployment. Protect remote endpoints with TLS and follow current MCP authorization guidance where applicable.
- Treat tool results, resource contents, and prompt arguments as untrusted. Avoid returning secrets and unnecessary records.
- Add timeouts, cancellation, bounded output, rate limiting, and safe logging.
- Test malformed messages, unknown methods, invalid arguments, unauthorized requests, oversized output, dependency failures, and repeated side effects.
- Document installation, configuration, required permissions, data handling, supported protocol/client versions, and operational limitations.
Tool design
- Use read-only tools by default where they meet the task.
- Separate read and write operations.
- Require confirmation or a server-side policy gate for destructive or consequential actions.
- Use idempotency for writes that clients may retry.
- Return structured, concise results with stable identifiers and provenance.
- Never treat a tool description as an authorization boundary.
Security review
Check path traversal, command injection, SSRF, secret leakage, overly broad OAuth scopes, token audience/issuer validation, confused-deputy risks, cross-tenant access, and prompt injection via resources. Validate origin and transport assumptions for the actual client/server topology.
Deliverable
Provide the capability inventory, schemas, auth/permission model, transport configuration, error taxonomy, tests, setup documentation, and a threat model.
References
- MCP specification: https://modelcontextprotocol.io/specification
- MCP security best practices: https://modelcontextprotocol.io/specification/draft/basic/security_best_practices
- Anthropic MCP overview: https://docs.anthropic.com/en/docs/agents-and-tools/mcp
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
- Pantani/ableton-mind★ 9same 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.
Used alongsideProjects with it also use infrastructure-as-code.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
mmondoraSkillinfrastructure-as-code
Infrastructure as Code with Terraform and Pulumi. State management, modularity, drift detection, secrets handling. Use when provisioning cloud resources, writing Terraform/Pulumi modules, or managing infrastructure configuration.
Also in 3 projects that use this
In this repository28 other files it gives its agents.
- agent-architecture-designSkill
- agent-evaluationSkill
- agent-harness-engineeringSkill
- agentic-workflow-testingSkill
- agent-memory-designSkill
- browser-computer-useSkill
- durable-agent-workflowsSkill
- human-in-the-loopSkill
- mcp-developmentSkill
- multi-agent-orchestrationSkill
- tool-calling-designSkill
- advanced-retrieval-rerankingSkill
- context-engineeringSkill
- embedding-model-engineeringSkill
- llm-evaluationSkill
- llm-observabilitySkill
- model-serving-inferenceSkill
- multimodal-ai-pipelinesSkill
- prompt-engineeringSkill
- rag-engineeringSkill
- rag-pipeline-engineeringSkill
- structured-outputsSkill
- agentic-securitySkill
- security-reviewSkill
- code-reviewSkill
- debuggingSkill
- test-engineeringSkill
- example-skillSkill
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.