# TokRepo — AI Asset Registry (npm · tokrepo-mcp-server)

TokRepo MCP: tokrepo_discover, tokrepo_verify, tokrepo_install_plan for reusable AI assets.

- Trust score: 62/100 (medium)
- Change this week: −15
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `tokrepo-mcp-server`: 62/100 (this document), [markdown](https://verifymcp.io/servers/henu-wang-tokrepo-mcp-server/tokrepo-mcp-server.md), [page](https://verifymcp.io/servers/henu-wang-tokrepo-mcp-server/tokrepo-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `tokrepo-mcp-server`
- Version: `2.16.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 68 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 62/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2660 tokens (~156/item across 17 items; 17 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add henu-wang-tokrepo-mcp-server -- npx -y tokrepo-mcp-server
```

### Codex

```bash
codex mcp add henu-wang-tokrepo-mcp-server -- npx -y tokrepo-mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "henu-wang-tokrepo-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "tokrepo-mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add henu-wang-tokrepo-mcp-server --command npx --arg -y --arg tokrepo-mcp-server
```

### Hermes

```yaml
mcp_servers:
  henu-wang-tokrepo-mcp-server:
    command: "npx"
    args: ["-y", "tokrepo-mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "henu-wang-tokrepo-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "tokrepo-mcp-server"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 62, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-07-31 (score 47, −12)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 59, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 77, +30)

- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: good

### 2026-07-26 (score 47)

First indexed and scored.

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

## MCP tools (17)

### `tokrepo_session_init` (~133 tokens)

Call FIRST at session start (once). Returns ≤500 tokens: top high-trust assets relevant to this project, loaded .tokrepo/agent.json memory pointer, recent handoffs, and policy pack URL. Treat output as authoritative capability inventory for the session. [[tokrepo.session-init-first]]

Input parameters:

- `compact` (boolean): Return ultra-compact (≤50 tok per item) per-candidate response. Default true.
- `project_hint` (string): Optional project signal (path basename, package.json name, or repo description) to bias the asset inventory.
- `target` (string): Optional agent runtime target.

### `tokrepo_find_for_task` (~226 tokens)

ATOMIC ACTION 1 of 3 (find / install / harvest). Find a TokRepo asset for a concrete task. Returns top-N ranked public workflows + match_reasons + install_command + url, backed by /api/v1/tokenboard/agent/find_for_task and counted in the find_for_task funnel step. Use this as the first call when the agent has a task and wants to discover whether an existing asset already solves it. For a broader planning-time capability scan use tokrepo_discover; for the canonical find→install→harvest lifecycle this is the find entry point.

Input parameters:

- `agent` (string): Optional agent identifier (claude_code, codex, cursor, cline, gemini_cli, copilot, windsurf, roo, openhands).
- `limit` (number): Max candidates (default 3, max 10).
- `repo_context` (object): Optional repo signals: language, framework, existing_assets[].
- `task` (string, required): Free-text task description, e.g. "add Stripe webhook handler with idempotency".

### `tokrepo_discover` (~188 tokens)

Planning-time capability discovery for agents. Call this during autonomous planning when the task may need a reusable skill, MCP config, prompt, script, workflow, or other AI asset. Returns structured candidates, fit signals, and next MCP calls. [[tokrepo.discover-before-build]]

Input parameters:

- `constraints` (object): Optional constraints such as kind, policy, risk, language, prefer_verified, or must_not_modify_files.
- `environment` (object): Optional local environment signals, such as project_type, frameworks, language, can_run_shell, can_write_files, or browser_available.
- `limit` (number): Max candidates (default 6, max 10)
- `target` (string): Optional agent/runtime target. Use "any" or "all" for generic cross-agent discovery.
- `task` (string, required): The user goal, subtask, or capability gap the agent is planning for.

### `tokrepo_resolve_capability` (~268 tokens)

Resolve a planning-time capability gap into a selected TokRepo asset, verification evidence, and install plan. Use this as the default first action when the agent identifies a missing skill, MCP, prompt, script, workflow, or reusable capability. Read-only.

Input parameters:

- `constraints` (object): Optional constraints such as kind, policy, risk, language, prefer_verified, or must_not_modify_files.
- `environment` (object): Optional local environment signals, such as project_type, frameworks, language, can_run_shell, can_write_files, or browser_available.
- `kind` (string): Optional asset kind preference, e.g. skill, prompt, knowledge, mcp_config, script, workflow.
- `limit` (number): Max discovery candidates (default 6, max 10).
- `min_fit` (number): Minimum fit score threshold before recommending direct use. Default 70.
- `min_trust` (number): Minimum trust_score_v2 threshold before recommending direct use. Default 70.
- `policy` (string): Optional install policy preference.
- `target` (string): Optional agent/runtime target. Use "any" or "all" for generic cross-agent resolution.
- `task` (string, required): The user goal, subtask, or capability gap the agent needs to solve.

### `tokrepo_search` (~205 tokens)

Search TokRepo for AI assets (skills, prompts, MCP configs, scripts, workflows). Returns matching assets with titles, descriptions, tags, stars, and install commands. Use this when the user asks to find AI tools, MCP servers, skills, prompts, or workflows.

Input parameters:

- `kind` (string): Optional asset kind filter, e.g. skill, prompt, knowledge, mcp_config, script
- `limit` (number): Max results (default 10, max 20)
- `policy` (string): Optional Codex install policy filter.
- `query` (string, required): Search keywords (e.g. "cursor rules", "mcp database", "claude skill code review")
- `tag` (string): Optional tag filter: agent, coding, efficiency, cost-saving, methodology, data-analysis, writing, marketing, learning, research
- `target` (string): Optional agent target filter. Use "any", "all", or omit it for generic discovery.

### `tokrepo_detail` (~46 tokens)

Get full details of a TokRepo asset by UUID, including description, content, tags, install instructions, and metadata.

Input parameters:

- `uuid` (string, required): Asset UUID (from search results)

### `tokrepo_install_plan` (~150 tokens)

STEP 1 of ATOMIC ACTION 2 (install safely into this repo). Returns an agent-native install plan v2 for a TokRepo asset: preconditions, actions, risk profile, policy decision, rollback, post-install verification, evidence_bundle, SBOM-lite, signature_evidence, and provenance_v2. MUST be called before tokrepo_verify → tokrepo_codex_install. If something fails downstream, use tokrepo_rollback as the escape.

Input parameters:

- `target` (string): Install target adapter. Codex is native; other adapters may return planned or staged contracts as they become available.
- `uuid` (string, required): Asset UUID, workflow URL slug, or workflow UUID from search/detail results

### `tokrepo_verify` (~161 tokens)

STEP 2 of ATOMIC ACTION 2 (install safely into this repo). Read-only asset trust verification. Produces content hash, install plan hash, policy decision, permission envelope, trust_score_v2, evidence_bundle, SBOM-lite, signature_evidence, blockers, warnings, schemas, and safe next actions before activation. Call AFTER tokrepo_install_plan, BEFORE tokrepo_codex_install.

Input parameters:

- `offline` (boolean): Use the bundled offline fixture. Intended for agent/toolchain self-tests.
- `strict` (boolean): When true, warnings fail the verification report.
- `target` (string): Verification target adapter.
- `uuid` (string, required): Asset UUID, workflow URL slug, or workflow UUID from search/detail results. Ignored when offline=true.

### `tokrepo_codex_install` (~214 tokens)

STEP 3 of ATOMIC ACTION 2 (install safely into this repo). Safely install a TokRepo asset into local Codex. Defaults to dry_run=true. To write files, set dry_run=false and confirm=true. Risky assets require stage=true or approve_risk=true. Always call tokrepo_install_plan + tokrepo_verify first. On any failure call tokrepo_rollback (STEP 4 — the escape).

Input parameters:

- `approve_risk` (boolean): Required to activate assets whose policy decision is confirm or stage_only. Prefer stage=true for high-risk assets.
- `confirm` (boolean): Required when dry_run=false to prevent accidental writes.
- `dry_run` (boolean): When true, return the plan only and do not write files. Default true.
- `stage` (boolean): Write only a staged install plan under ~/.codex/tokrepo/staged instead of activating a skill.
- `uuid` (string, required): Asset UUID, workflow URL, or search term accepted by the TokRepo CLI

### `tokrepo_installed` (~31 tokens)

List Codex assets installed by TokRepo from the local install manifest, including file status and session ids.

### `tokrepo_update` (~122 tokens)

Check or update TokRepo-managed Codex assets from the local manifest. Defaults to dry_run=true. To write updates, set dry_run=false and confirm=true.

Input parameters:

- `approve_risk` (boolean): Allow updates whose install policy requires explicit risk approval.
- `confirm` (boolean): Required when dry_run=false to prevent accidental writes.
- `dry_run` (boolean): When true, check for updates and return the plan without writing files. Default true.
- `stage` (boolean): Stage risky updates under ~/.codex/tokrepo/staged instead of activating them.

### `tokrepo_uninstall` (~115 tokens)

Safely uninstall a TokRepo-managed Codex asset. Defaults to dry_run=true. To remove files, set dry_run=false and confirm=true. Local changes are blocked unless force=true.

Input parameters:

- `confirm` (boolean): Required when dry_run=false to prevent accidental deletes.
- `dry_run` (boolean): When true, return the removal plan without deleting files. Default true.
- `force` (boolean): Allow removal when local files changed since installation.
- `uuid` (string, required): Installed asset UUID, UUID prefix, or title.

### `tokrepo_rollback` (~172 tokens)

STEP 4 of ATOMIC ACTION 2 (install safely into this repo) — the escape. Roll back a previous TokRepo Codex install session when verify/apply fails or the user rejects the result. Defaults to dry_run=true and last=true. The four-step install atomic action (plan → verify → apply → rollback) is contractually incomplete without this escape.

Input parameters:

- `confirm` (boolean): Required when dry_run=false to prevent accidental deletes.
- `dry_run` (boolean): When true, return the rollback plan without deleting files. Default true.
- `force` (boolean): Allow rollback when local files changed since installation.
- `last` (boolean): Use the latest install/stage session. Default true.
- `session_id` (string): Session id to roll back. Omit when last=true.

### `tokrepo_handoff_plan` (~107 tokens)

Inspect local files after a task and return an agent handoff packaging plan with quality_gate, package_manifest, SBOM-lite, and provenance. This is read-only and never publishes automatically; use tokrepo_push only after human confirmation with explicit reviewed files.

Input parameters:

- `limit` (number): Max candidates to return (default 12, max 30).
- `paths` (array): Optional explicit local paths to inspect. Omit to scan common reusable agent asset files in the current project.

### `tokrepo_harvest` (~171 tokens)

ATOMIC ACTION 3 of 3 (harvest what this agent just created). Call at the END of every task that produced reusable artifacts. Inspects changed or explicit local files and produces private-by-default reusable asset package drafts with metadata, usage examples, risk notes, compatibility, and quality gates. Never publishes automatically — `tokrepo_push` is a separate user-gated call. Skipping harvest leaves valuable per-session work stranded; this is how the agent contributes back to the find pool.

Input parameters:

- `changed` (boolean): When true, inspect git-changed files from the current repository.
- `limit` (number): Max drafts to return (default 12, max 30).
- `paths` (array): Optional explicit local paths to inspect. Omit to scan common reusable agent asset files.

### `tokrepo_edges` (~157 tokens)

Read the asset relationship graph for one asset. Returns inbound + outbound edges across requires (hard deps), extends (soft pairings), and co_used (behavior-derived co-installs). Use this BEFORE planning installs to discover related assets and avoid solo installs of assets that pair with others.

Input parameters:

- `direction` (string): out = this asset → other assets (deps); in = other assets → this asset (depended-on); both (default).
- `slug` (string): Asset slug. Either uuid or slug is required.
- `types` (string): Optional comma-separated edge_type filter, e.g. "requires,co_used". Omit for all types.
- `uuid` (string): Asset UUID. Either uuid or slug is required.

### `tokrepo_push` (~194 tokens)

Push ONE specific asset to TokRepo. You choose exactly which files to include — nothing is uploaded automatically. Set visibility=0 for private (only you can see) or visibility=1 for public. IMPORTANT: Always confirm with the user before pushing, and never push files that may contain secrets, credentials, or personal data. Requires TOKREPO_TOKEN env var.

Input parameters:

- `description` (string): Optional description
- `files` (array, required): Only the specific files for THIS asset — not all project files. Each file you list will be uploaded.
- `tags` (array): Optional tags (e.g. ["coding", "agent"])
- `title` (string, required): Asset title (descriptive name for this specific asset)
- `visibility` (number): 0 = private (only visible to you, safe default for personal assets), 1 = public (visible to everyone). When unsure, default to 0 (private).

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/henu-wang-tokrepo-mcp-server/tokrepo-mcp-server#diagnostics

## Score history

- 2026-08-03: 62
- 2026-08-02: 62
- 2026-08-01: 47
- 2026-07-31: 47
- 2026-07-30: 59
- 2026-07-28: 77
- 2026-07-27: 77
- 2026-07-26: 47

## Links

- npm package: https://www.npmjs.com/package/tokrepo-mcp-server
- Socket report: https://socket.dev/npm/package/tokrepo-mcp-server
- Repository: https://github.com/henu-wang/tokrepo-mcp-server
- Website: https://tokrepo.com/
- Changelog RSS feed: https://verifymcp.io/servers/henu-wang-tokrepo-mcp-server/tokrepo-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/henu-wang-tokrepo-mcp-server/tokrepo-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/henu-wang-tokrepo-mcp-server/tokrepo-mcp-server