// SCAN REPORT

TokRepo — AI Asset Registry

23 tools. 9 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 1 Jul 2026

9 can modify or destroy data

14 read-only

23 tools total

Community server · catalogue entry verified 01/07/2026

How to control TokRepo — AI Asset Registry ↓

TOOL MAP

What TokRepo — AI Asset Registry exposes to your agents

Read (14) Write / Execute (7) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous TokRepo — AI Asset Registry tools

Destructive · High tokrepo_uninstall Although the tool defaults to dry_run=true (a safety measure), it is designed to permanently delete or uninstall managed assets and files when confirm=true and dry_run=false are set. Destructive · High tokrepo_rollback A rollback operation reverts previously applied changes, which constitutes an irreversible destructive action on the installed state. Execute · High tokrepo_eval_agent This tool executes evaluation and verification operations against external systems (install plans, manifests, Codex installs) and can perform rollback actions that modify local state. Execute · High tokrepo_install While the tool may appear to only fetch data, its explicit purpose is to return content 'ready to be executed' or saved as runnable files (MCP configs, workflows, scripts).

9 of TokRepo — AI Asset Registry's 23 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control TokRepo — AI Asset Registry

PolicyLayer is an MCP gateway — it sits between your AI agents and TokRepo — AI Asset Registry, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "tokrepo_rollback": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "tokrepo_codex_install": {
    "limits": [
      {
        "counter": "tokrepo_codex_install_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "tokrepo_clone_plan": {
    "limits": [
      {
        "counter": "tokrepo_clone_plan_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register TokRepo — AI Asset Registry — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON TOKREPO — AI ASSET REGISTRY →

Instant setup, no code required.

FULL CATALOGUE

All 23 TokRepo — AI Asset Registry tools

DESTRUCTIVE 2 tools

Destructive tokrepo_rollback STEP 4 of ATOMIC ACTION 2 (install safely into this repo) — the escape. Roll back a previous TokRepo Codex ins Destructive tokrepo_uninstall Safely uninstall a TokRepo-managed Codex asset. Defaults to dry_run=true. To remove files, set dry_run=false a

EXECUTE 2 tools

Execute tokrepo_eval_agent Run TokRepo agent-native evals through the CLI. Verifies filtered search, install-plan contracts, metadata qua Execute tokrepo_install Get the install command and raw content for a TokRepo asset. Returns the content ready to be saved to a file o

WRITE 5 tools

Write tokrepo_codex_install STEP 3 of ATOMIC ACTION 2 (install safely into this repo). Safely install a TokRepo asset into local Codex. De Write tokrepo_harvest ATOMIC ACTION 3 of 3 (harvest what this agent just created). Call at the END of every task that produced reusa Write tokrepo_install_plan STEP 1 of ATOMIC ACTION 2 (install safely into this repo). Returns an agent-native install plan v2 for a TokRe Write tokrepo_push Push ONE specific asset to TokRepo. You choose exactly which files to include — nothing is uploaded automatica Write tokrepo_update Check or update TokRepo-managed Codex assets from the local manifest. Defaults to dry_run=true. To write updat

READ 14 tools

Read tokrepo_clone_plan Plan a bulk Codex install from a TokRepo user profile using the TokRepo CLI. Returns JSON dry-run output witho Read tokrepo_detail Get full details of a TokRepo asset by UUID, including description, content, tags, install instructions, and m Read tokrepo_discover Planning-time capability discovery for agents. Call this during autonomous planning when the task may need a r Read tokrepo_edges Read the asset relationship graph for one asset. Returns inbound + outbound edges across requires (hard deps), Read tokrepo_find_for_task ATOMIC ACTION 1 of 3 (find / install / harvest). Find a TokRepo asset for a concrete task. Returns top-N ranke Read tokrepo_handoff_plan Inspect local files after a task and return an agent handoff packaging plan with quality_gate, package_manifes Read tokrepo_installed List Codex assets installed by TokRepo from the local install manifest, including file status and session ids. Read tokrepo_list_my List all assets owned by the authenticated user. Requires TOKREPO_TOKEN env var. Read tokrepo_resolve_capability Resolve a planning-time capability gap into a selected TokRepo asset, verification evidence, and install plan. Read tokrepo_search Search TokRepo for AI assets (skills, prompts, MCP configs, scripts, workflows). Returns matching assets with Read tokrepo_session_init Call FIRST at session start (once). Returns ≤500 tokens: top high-trust assets relevant to this project, loade Read tokrepo_status Compare local files against remote TokRepo assets. Returns new/updated/unchanged status for each asset. Like Read tokrepo_trending Get trending/popular AI assets on TokRepo. Use when user asks for recommended or popular AI tools. Read tokrepo_verify STEP 2 of ATOMIC ACTION 2 (install safely into this repo). Read-only asset trust verification. Produces conten

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about TokRepo — AI Asset Registry

Can an AI agent delete data through the TokRepo — AI Asset Registry MCP server? +

Yes. The TokRepo — AI Asset Registry server exposes 2 destructive tools including tokrepo_rollback, tokrepo_uninstall. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through TokRepo — AI Asset Registry? +

The TokRepo — AI Asset Registry server has 5 write tools including tokrepo_codex_install, tokrepo_harvest, tokrepo_install_plan. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach TokRepo — AI Asset Registry.

How many tools does the TokRepo — AI Asset Registry MCP server expose? +

23 tools across 4 categories: Destructive, Execute, Read, Write. 14 are read-only. 9 can modify, create, or delete data.

How do I enforce a policy on TokRepo — AI Asset Registry? +

Register the TokRepo — AI Asset Registry MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every TokRepo — AI Asset Registry tool call.

Deterministic rules across all 23 TokRepo — AI Asset Registry tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TOKREPO — AI ASSET REGISTRY →

Instant setup, no code required.

23 TokRepo — AI Asset Registry tools catalogued and risk-classified — across an index of 43,000+ MCP servers.