{
  "markdown": "# TokRepo MCP Server\n\n> Agent-native MCP server for TokRepo: session bootstrap, capability discovery, search/detail, trust verification, install planning, Codex staging, lifecycle inspection/update/uninstall/rollback, handoff/harvest planning, and human-confirmed publishing of reusable AI assets.\n\n[![npm](https://img.shields.io/npm/v/tokrepo-mcp-server)](https://www.npmjs.com/package/tokrepo-mcp-server)\n[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)\n\n## Quick Start\n\n### Claude Code\n```bash\nclaude mcp add tokrepo -- npx -y tokrepo-mcp-server\n```\n\n### Cursor / Windsurf\nAdd to your MCP config (`~/.cursor/mcp.json`):\n```json\n{\n  \"mcpServers\": {\n    \"tokrepo\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"tokrepo-mcp-server\"]\n    }\n  }\n}\n```\n\n### OpenAI Codex / Gemini CLI\n```bash\ncodex mcp add tokrepo -- npx -y tokrepo-mcp-server\ngemini settings mcp add tokrepo -- npx -y tokrepo-mcp-server\n```\n\n## What It Does\n\nOnce connected, your AI assistant can:\n\n- **Discover during planning** — turn a task or capability gap into structured candidate skills, prompts, MCP configs, scripts, and workflows\n- **Resolve capability gaps** — select a candidate with verification evidence, install plan, lifecycle contract, next MCP calls, and CLI fallbacks before local build\n- **Search** public AI assets by keyword or category with agent fit signals\n- **Browse** trending assets, filter by type (MCP, Skill, Prompt, Agent, Script)\n- **Get details** — full documentation, install instructions, and metadata\n- **Verify trust** — read-only content hash, install plan hash, permission envelope, policy, trust_score_v2, `evidence_bundle`, SBOM-lite, `signature_evidence`, blockers, and warnings\n- **Plan before install** — get install plan v2 with policy decisions, rollback, verification, `evidence_bundle`, SBOM-lite, and `signature_evidence`\n- **Safe Codex install** — dry-run by default; risky assets must be staged or explicitly approved\n- **Lifecycle control** — list, update, uninstall, and roll back managed Codex installs\n- **Post-task harvest** — inspect changed or explicit local files with `tokrepo_harvest` before any push, including private package drafts, `quality_gate`, package manifest, SBOM-lite, and provenance\n- **Project memory** — pair with `tokrepo init-agent --target all` so future agents know to call TokRepo during planning\n- **Discovery surfaces** — official MCP `server.json`, A2A agent card, portable agent manifest, tool catalog, `.well-known`, `agents.txt`, `llms.txt`, and npm metadata are kept machine-readable for agents and registries\n- **Funnel visibility** — anonymous aggregate events show whether agents actually discover, plan, install, hand off, and push reusable assets\n\n## Available Tools\n\n| Tool | Description |\n|------|-------------|\n| `tokrepo_session_init` | Session bootstrap with high-trust assets, project memory pointer, recent handoffs, and policy pack URL |\n| `tokrepo_discover` | Planning-time capability discovery from a task, environment, and constraints |\n| `tokrepo_find_for_task` | Atomic find action for a concrete task; returns ranked assets, match reasons, install command, and URL |\n| `tokrepo_resolve_capability` | Resolve a capability gap into a selected asset, verification evidence, install plan, lifecycle contract, next MCP calls, and CLI fallbacks |\n| `tokrepo_search` | Search assets by keyword/tag with `agent_fit` ranking |\n| `tokrepo_detail` | Get full asset details by UUID |\n| `tokrepo_edges` | Inspect requires, extends, and co-used asset graph edges before planning installs |\n| `tokrepo_install_plan` | Get agent-native install plan v2 with rollback, evidence_bundle, SBOM-lite, and signature_evidence |\n| `tokrepo_verify` | Verify trust, hashes, permissions, policy, evidence_bundle, SBOM-lite, and signature_evidence before activation |\n| `tokrepo_codex_install` | Dry-run, stage, or install a Codex skill safely |\n| `tokrepo_installed` | List TokRepo-managed Codex installs |\n| `tokrepo_update` | Dry-run or update managed Codex installs |\n| `tokrepo_uninstall` | Dry-run or remove a managed Codex install |\n| `tokrepo_rollback` | Dry-run or roll back a prior Codex install session |\n| `tokrepo_handoff_plan` | Read-only packaging plan with quality_gate and package manifest for reusable local work after a task |\n| `tokrepo_harvest` | Read-only package draft generator for reusable changed or explicit local files after a task |\n| `tokrepo_push` | Push one explicit asset to TokRepo after user confirmation |\n\n## Example Conversations\n\n```\nYou: \"Find me a good MCP server for databases\"\nAI: [calls tokrepo_resolve_capability] → Ranks DBHub, Supabase MCP, PostgreSQL MCP and returns verification/install-plan evidence for the selected candidate\n\nYou: \"What video assets should I install?\"\nAI: [calls tokrepo_resolve_capability] → Finds relevant skills, checks fit, trust, and policy, then asks before installing\n\nYou: \"Install that cursor rules asset\"\nAI: [calls tokrepo_verify] → Checks trust_score_v2, permissions, blockers, and warnings\nAI: [calls tokrepo_install_plan] → Reviews policy and actions\nAI: [calls tokrepo_codex_install with dry_run=false, confirm=true] → Writes only after explicit confirmation\nAI: [calls tokrepo_rollback with dry_run=true] → Shows exactly what would be removed before rollback\n\nYou: \"We created a reusable project rule; save it for future agents\"\nAI: [calls tokrepo_harvest] → Returns explicit files, hashes, quality_gate, package drafts, SBOM-lite, provenance, metadata defaults, and private-by-default push guidance\nAI: [asks for confirmation before tokrepo_push] → Uploads only reviewed files\n```\n\n## Make Future Agents Discover TokRepo\n\nRun this once in a project:\n\n```bash\nnpx tokrepo init-agent --target all\n```\n\nIt writes managed instructions to `AGENTS.md`, `CLAUDE.md`, `GEMINI.md`, Cursor rules, GitHub Copilot instructions, Cline rules, Windsurf rules, Roo rules, OpenHands microagents, Aider conventions, `.mcp.json`, and `.tokrepo/agent.json`. The rule is simple: during planning, when the agent sees a capability gap, it should call `tokrepo_resolve_capability` or `tokrepo_discover` before inventing a one-off local tool. After a task, agents can call `tokrepo_harvest` or run `tokrepo harvest --changed --json` to suggest reusable files for user-confirmed private publishing.\n\n## Machine-Readable Listing\n\nRegistries and agents can discover this server through:\n\n- MCP server manifest: [tokrepo.com/.well-known/mcp/server.json](https://tokrepo.com/.well-known/mcp/server.json)\n- TokRepo manifest: [tokrepo.com/.well-known/tokrepo.json](https://tokrepo.com/.well-known/tokrepo.json)\n- Portable agent manifest: [tokrepo.com/.well-known/agent.json](https://tokrepo.com/.well-known/agent.json)\n- A2A agent card: [tokrepo.com/.well-known/agent-card.json](https://tokrepo.com/.well-known/agent-card.json)\n- Tool catalog: [tokrepo.com/.well-known/tool-catalog.json](https://tokrepo.com/.well-known/tool-catalog.json)\n- Trust manifest: [tokrepo.com/.well-known/tokrepo-trust.json](https://tokrepo.com/.well-known/tokrepo-trust.json)\n- Default agent policy pack: [tokrepo.com/policy-packs/default-agent-policy.json](https://tokrepo.com/policy-packs/default-agent-policy.json)\n- Eval evidence: [tokrepo.com/evals/agent-discovery.json](https://tokrepo.com/evals/agent-discovery.json)\n- Multi-agent compatibility: [tokrepo.com/evals/multi-agent-compatibility.json](https://tokrepo.com/evals/multi-agent-compatibility.json)\n- Agent memory schema: [tokrepo.com/schemas/agent-memory.schema.json](https://tokrepo.com/schemas/agent-memory.schema.json)\n- Agent evidence bundle schema: [tokrepo.com/schemas/agent-evidence-bundle.schema.json](https://tokrepo.com/schemas/agent-evidence-bundle.schema.json)\n- Capability resolution schema: [tokrepo.com/schemas/capability-resolution.schema.json](https://tokrepo.com/schemas/capability-resolution.schema.json)\n- Harvest report schema: [tokrepo.com/schemas/harvest-report.schema.json](https://tokrepo.com/schemas/harvest-report.schema.json)\n- Handoff package schema: [tokrepo.com/schemas/handoff-package.schema.json](https://tokrepo.com/schemas/handoff-package.schema.json)\n- Agent text entry: [tokrepo.com/agents.txt](https://tokrepo.com/agents.txt)\n- Agent instructions: [tokrepo.com/agent-instructions/tokrepo.md](https://tokrepo.com/agent-instructions/tokrepo.md)\n- Agent ecosystem distribution pack: [tokrepo.com/agent-ecosystem.json](https://tokrepo.com/agent-ecosystem.json)\n- LLM crawler entry: [tokrepo.com/llms.txt](https://tokrepo.com/llms.txt)\n\nUse `https://tokrepo.com/agent-ecosystem.json` for agent marketplace submissions, starter templates, README snippets, install guides, and example projects. It contains canonical listing copy, ecosystem channels, target project-memory files, and verification commands.\n\nTokRepo emits anonymous aggregate funnel events for `tokrepo_resolve_capability`, `tokrepo_discover`, `tokrepo_verify`, `tokrepo_install_plan`, install dry-runs, installs, harvests, handoffs, and pushes. It does not send task text or file contents. Disable with `TOKREPO_TELEMETRY=0`.\n\n## Why TokRepo?\n\nTokRepo is the **open registry for AI assets** — like npm for packages, but for AI skills, prompts, MCP configs, and workflows.\n\n- **Curated assets** — quality-reviewed, not a dump\n- **Agent-native** — every asset has machine-readable install contracts\n- **Universal** — works with Claude Code, Cursor, Codex, Gemini CLI, and any MCP client\n- **CLI available** — `npx tokrepo search \"query\"` / `npx tokrepo install <uuid>`\n\n## Requirements\n\n- Node.js >= 18\n- Internet connection (queries tokrepo.com API)\n\n## Links\n\n- **Website**: [tokrepo.com](https://tokrepo.com)\n- **CLI**: [npm: tokrepo](https://www.npmjs.com/package/tokrepo)\n- **GitHub**: [henu-wang/tokrepo-mcp-server](https://github.com/henu-wang/tokrepo-mcp-server)\n- **API**: [tokrepo.com/.well-known/tokrepo.json](https://tokrepo.com/.well-known/tokrepo.json)\n\n## License\n\nMIT\n",
  "bytes": 9979,
  "sha": "d05965997753736b5f0e9df9ce1696023944aac7b27594c6698163ade314de86",
  "repo_slug": "henu-wang/tokrepo-mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_henu_wang_tokrepo_mcp_server_1b362c24/readme"
}