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.

Install with Tessl CLI

npx tessl i github:secondsky/claude-skills --skill mcp-management

What are skills?

Review — 77%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 10 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

95%

65%

Bootstrap MCP Integration for AI Agent Project

MCP environment setup and configuration

Criteria

Without context

With context

MCP config location

100%

Gemini symlink command

100%

Gemini directory creation

50%

100%

Bun for Gemini install

66%

Global flag used

100%

MCP config structure

100%

Single config, dual use

100%

Without context: $0.2950 · 1m 10s · 13 turns · 14 in / 4,355 out tokens

With context: $0.3765 · 1m 15s · 19 turns · 109 in / 4,191 out tokens

65%

45%

Build an MCP Tool Catalog System

MCP capability discovery and tool catalog

Criteria

Without context

With context

bunx tsx for discovery

100%

list-prompts command

100%

list-resources command

100%

Output to assets/tools.json

100%

LLM reads catalog file

Catalog as context input

Multi-server aggregation

100%

Server identification

100%

Without context: $0.6444 · 3m 5s · 27 turns · 122 in / 9,966 out tokens

With context: $0.3747 · 1m 15s · 16 turns · 17 in / 4,642 out tokens

100%

69%

Implement a Robust MCP Task Execution System

MCP execution priority and fallback strategy

Criteria

Without context

With context

Gemini CLI first

100%

Availability check

100%

Correct Gemini model

100%

Gemini -y flag

100%

Direct scripts secondary

100%

call-tool syntax

100%

Subagent fallback

100%

Three-tier priority

100%

Context clean rationale

12%

100%

Conditional fallback logic

100%

Without context: $0.4437 · 2m 28s · 13 turns · 13 in / 9,059 out tokens

With context: $0.3324 · 1m 13s · 14 turns · 262 in / 4,449 out tokens

Evaluated: 3 days ago
Agent: Claude Code

Table of Contents

Bootstrap MCP Integration for AI Agent Project Build an MCP Tool Catalog System Implement a Robust MCP Task Execution System

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.