Capytail
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Capytail
A local MCP capability router that selects relevant skills before loading context.
Capytail is a selector, not an execution gateway. It helps agents avoid loading every skill, agent, or MCP recommendation into context up front.
Status
Experimental 0.1.x.
Use it when you want:
compact capability routing;
read-only MCP runtime tools;
local CLI ingestion for trusted skills;
deterministic selection before optional full skill loading.
Do not use it as:
an MCP proxy;
an agent orchestrator;
persistent memory;
a RAG/vector database;
a remote skill installer.
Related MCP server: skill-router-mcp
Install
npm install -g capytailFrom source:
npm install
npm run build
node dist/src/cli.js --helpMCP runtime
Start the read-only MCP server:
capytail mcpPublic MCP tools:
Tool | Purpose |
| Select relevant capabilities for a request. |
| List compact discovered capabilities. |
| Fetch full content for one selected local skill/agent id. |
Normal agent flow:
capytail_route({ request })
→ capytail_get_capability({ id })route and list return compact metadata only. They do not return full skill bodies.
CLI admin
Add a local skill after a static SkillSpector scan:
capytail add-skill ./my-skill
capytail add-skill ./my-skill --project-root . --name my-skill
capytail add-skill ./my-skill --allow-mediumThe CLI uses a fixed scanner path:
$HOME/.pi/agent/tools/skillspector/.venv/bin/skillspector--skillspector-path is intentionally rejected.
When a skill is accepted, Capytail copies it into:
.capytail/skills/<name>/Then it enriches the copied SKILL.md with missing routing metadata:
aliases: <name>
triggers: ...
use_when: ...It also associates the skill with the current project using the existing capability graph:
{
"graph": {
"projectId": "project:my-project",
"edges": [
{
"from": "project:my-project",
"relation": "project_has_skill",
"to": "skill:project:my-skill"
}
]
}
}The original source skill is not modified.
Configuration
Capytail reads capytail.config.json or .capytail/config.json from the project root.
See examples/capytail.config.json.
Benchmarks
In a local corpus of 43 SKILL.md files:
Flow | Approx tokens | Time |
Load all skills | ~121k | n/a |
| ~1.0k–1.3k | ~10–15ms |
| ~7.4k–40.8k | ~63–80ms |
See docs/benchmarks.md.
Security model
See SECURITY.md and docs/security-model.md.
Short version:
MCP surface is read-only.
Skill ingestion is CLI-only.
Local paths only.
Static SkillSpector scan only,
--no-llm.No remote URL ingestion.
No dependency installation.
No skill execution.
Development
npm test
npm run typecheck
npm run buildLicense
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Governed AI agent skills — one library, distributed to devs and exposed to remote agents over MCP.
MCP-Native LLM Orchestration Agent
Hosted MCP server and Agent Skills for specs, engineering threads, and project memory.
Agent communication platform for agent to agent messaging via MCP. Messages, channels, skills.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceSkillMesh is a retrieval router for MCP/LLM tool catalogs. It selects top-K relevant expert cards instead of loading every tool, reducing prompt size, by improving tool selection, and lowering token cost. Supports Claude MCP, Codex skills, and OpenAI-style function schemas.43 PyPI7MIT
- AlicenseAqualityDmaintenanceRoutes SKILL.md libraries to any MCP client, enabling task matching and skill loading with embedding-based scoring, keyword fallback, and context-window discipline.528 npmMIT
- FlicenseNot gradedqualityDmaintenanceEnterprise-grade intent routing gateway implementing the Model Context Protocol (MCP) spec, optimizing context by routing queries to specialized sub-nodes to reduce token overhead by 85% with negligible latency overhead.-
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to keep skill catalogs outside the main LLM context and load only task-relevant SKILL.md instructions via a single MCP tool, reducing context overhead.4MIT