CtrlK
BlogDocsLog inGet started
Tessl Logo

mcp-management

Manage MCP servers - discover, analyze, execute tools/prompts/resources. Use for MCP integrations, capability discovery, tool filtering, programmatic execution, or encountering context bloat, server configuration, tool execution errors.

82

3.18x
Quality

77%

Does it follow best practices?

Impact

86%

3.18x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/mcp-management/skills/mcp-management/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

95%

65%

Bootstrap MCP Integration for AI Agent Project

MCP environment setup and configuration

Criteria
Without context
With context

MCP config location

0%

100%

Gemini symlink command

0%

100%

Gemini directory creation

50%

100%

Bun for Gemini install

0%

66%

Global flag used

100%

100%

MCP config structure

100%

100%

Single config, dual use

0%

100%

65%

45%

Build an MCP Tool Catalog System

MCP capability discovery and tool catalog

Criteria
Without context
With context

bunx tsx for discovery

0%

100%

list-prompts command

0%

100%

list-resources command

0%

100%

Output to assets/tools.json

0%

100%

LLM reads catalog file

0%

0%

Catalog as context input

0%

0%

Multi-server aggregation

100%

100%

Server identification

100%

100%

100%

69%

Implement a Robust MCP Task Execution System

MCP execution priority and fallback strategy

Criteria
Without context
With context

Gemini CLI first

100%

100%

Availability check

100%

100%

Correct Gemini model

0%

100%

Gemini -y flag

0%

100%

Direct scripts secondary

0%

100%

call-tool syntax

0%

100%

Subagent fallback

0%

100%

Three-tier priority

0%

100%

Context clean rationale

12%

100%

Conditional fallback logic

100%

100%

Repository
secondsky/claude-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.