// SCAN REPORT

Lithtrix

43 tools. 24 can modify or destroy data without limits.

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

Last updated: 3 Jul 2026

24 can modify or destroy data

19 read-only

43 tools total

Community server · catalogue entry verified 03/07/2026

How to control Lithtrix ↓

TOOL MAP

What Lithtrix exposes to your agents

Read (19) Write / Execute (18) Destructive / Financial (6)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Lithtrix tools

Financial · Critical lithtrix_passport_stake This tool locks/commits platform credits (a financial resource) to stake a tier. Financial · High lithtrix_passport_unstake Unstaking is a financial action that initiates the withdrawal of staked assets/tokens. Destructive · Critical lithtrix_keys_revoke This tool irreversibly deletes authentication keys/credentials. Destructive · High lithtrix_passport_revoke Revoking a passport is a destructive operation that cannot be undone without administrative intervention.

24 of Lithtrix's 43 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Lithtrix

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

Block financial tools by default

{
  "lithtrix_passport_stake": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Deny destructive operations

{
  "lithtrix_blob_delete": {
    "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

{
  "lithtrix_agent_vouch": {
    "limits": [
      {
        "counter": "lithtrix_agent_vouch_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "lithtrix_blob_download": {
    "limits": [
      {
        "counter": "lithtrix_blob_download_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 Lithtrix — 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 LITHTRIX →

Instant setup, no code required.

FULL CATALOGUE

All 43 Lithtrix tools

FINANCIAL 2 tools

Financial lithtrix_passport_stake POST /v1/agents/passport/stake — lock platform credits for passport stake tier (Bearer root ltx_). Financial lithtrix_passport_unstake POST /v1/agents/passport/unstake — begin unstake cooling period (Bearer root ltx_).

DESTRUCTIVE 4 tools

Destructive lithtrix_blob_delete Soft-delete a blob (DELETE /v1/blobs/{blob_id}). Requires LITHTRIX_API_KEY. Destructive lithtrix_keys_revoke Immediately revoke a scoped sub-key (DELETE /v1/keys/{key_id}). Root Bearer. Destructive lithtrix_passport_revoke POST /v1/me/passport/revoke — revoke passport (requires root ltx_ API key). Destructive lithtrix_passport_sponsor_revoke POST /v1/agents/{sponsor_id}/sponsor/{ward_id}/revoke — start sponsor revoke grace (Bearer must match sponsor_

EXECUTE 5 tools

Execute lithtrix_blob_parse POST /v1/blobs/{blob_id}/parse — extract text/tables; set async=true for QStash. Optional callback_url in JSON Execute lithtrix_browse Pay to be fully autonomous: server-side public web access for agents. Execute lithtrix_passport_auth_verify POST /v1/auth/passport/verify — exchange Ed25519 signature for ltx_session_ token. Execute lithtrix_passport_rotate POST /v1/me/passport/rotate — rotate Ed25519 passport (requires root LITHTRIX_API_KEY). Returns private_key on Execute lithtrix_spawn Spawn a scoped swarm child (POST /v1/agents/{parent_agent_id}/spawn). Requires root LITHTRIX_API_KEY.

WRITE 13 tools

Write lithtrix_agent_vouch POST /v1/agents/{target_agent_id}/vouch — vouch for a skill on another agent (Bearer = voucher). Write lithtrix_agent_vouch_revoke POST /v1/agents/{target_agent_id}/vouch/revoke — revoke your skill vouch (Bearer = voucher only). Write lithtrix_blob_upload Upload binary bytes via PUT /v1/blobs (raw body + Content-Type). Write lithtrix_feedback After lithtrix_search, send helpful / unhelpful / wrong signal using ref_type search_id and Write lithtrix_feedback_interaction POST /v1/feedback/interaction — agent-on-agent reputation signal (positive/negative/neutral). Write lithtrix_keys_create_scoped Create a scoped child API key (POST /v1/keys). Requires root Bearer; returns one-time api_key. Write lithtrix_memory_set Store or update a JSON value for a memory key (PUT /v1/memory/{key}). Write lithtrix_passport_set_capabilities POST /v1/agents/passport/capabilities — replace operator capabilities.self_reported (root ltx_ or ltx_session_ Write lithtrix_passport_set_description POST /v1/agents/passport/description — update bio, skills, listed, and/or reputation_sub_signal_visibility Write lithtrix_passport_sponsor POST /v1/agents/{sponsor_id}/sponsor/{ward_id} — vouch for ward (Bearer must match sponsor_id). Write lithtrix_register Register a new agent with Lithtrix and receive a one-time API key. Write lithtrix_reputation_dispute POST /v1/reputation/dispute — dispute a reputation event where you are the subject (max 3/UTC day). Write lithtrix_trace_append Append a task trace event (POST /v1/tasks/{task_id}/trace/events). Records only — no runtime veto.

READ 19 tools

Read lithtrix_blob_download Download blob bytes (GET /v1/blobs/{blob_id}). Returns JSON with content_base64 and content_type. Read lithtrix_blob_list List blob metadata (GET /v1/blobs). Optional page and per_page. Requires LITHTRIX_API_KEY. Read lithtrix_blob_meta Get JSON metadata for one blob (GET /v1/blobs/{blob_id}/meta). Requires LITHTRIX_API_KEY. Read lithtrix_blob_parse_status GET /v1/blobs/{blob_id}/parse/{parse_id} — poll parse status. Requires LITHTRIX_API_KEY. Read lithtrix_blob_search GET /v1/blobs/search — semantic search over parsed chunks; shares quota with web search. Requires LITHTRIX_API Read lithtrix_blob_signed_url Mint a time-limited HTTPS read URL for a blob (GET /v1/blobs/{blob_id}/signed-url). Read lithtrix_commons_read List opt-in shared public memory from Lithtrix Commons ( Read lithtrix_delegate Issue a signed delegation contract (POST /v1/agents/{parent_agent_id}/delegate). Signs locally with passport k Read lithtrix_keys_list List scoped sub-keys for this agent (GET /v1/keys). Requires the root LITHTRIX_API_KEY. Read lithtrix_keys_rotate Rotate a scoped sub-key (POST /v1/keys/{key_id}/rotate). Prior key honors grace_hours (default 24). Root Beare Read lithtrix_memory_context Reload top memories for session start (GET /v1/memory/context) — Read lithtrix_memory_get Retrieve a stored memory by key (GET /v1/memory/{key}). Requires LITHTRIX_API_KEY. Read lithtrix_memory_search Semantic search over your memories (GET /v1/memory/search). Read lithtrix_passport_auth_challenge POST /v1/auth/passport/challenge — mint short-lived nonce (no Bearer). Read lithtrix_passport_derive Derive deterministic Ed25519 passport PEMs locally from LITHTRIX_PASSPORT_MASTER_SEED + agent_id — never sends Read lithtrix_passport_ephemeral POST /v1/auth/passport/ephemeral — session-scoped Ed25519 passport + ltx_session_ for stateless sandboxes. Read lithtrix_passport_get GET /v1/agents/{agent_id}/passport — public DID + PEM public key (no authentication). Read lithtrix_search Search the web via Lithtrix and get credibility-scored results. Read lithtrix_trace_get Read task audit trace (GET /v1/tasks/{task_id}/trace). Task participant only.

EXPLORE

Related servers

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

FAQ

Questions about Lithtrix

Can an AI agent move money through the Lithtrix MCP server? +

Yes. The Lithtrix server exposes 2 financial tools including lithtrix_passport_stake, lithtrix_passport_unstake. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

Can an AI agent delete data through the Lithtrix MCP server? +

Yes. The Lithtrix server exposes 4 destructive tools including lithtrix_blob_delete, lithtrix_keys_revoke, lithtrix_passport_revoke. 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 Lithtrix? +

The Lithtrix server has 13 write tools including lithtrix_agent_vouch, lithtrix_agent_vouch_revoke, lithtrix_blob_upload. 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 Lithtrix.

How many tools does the Lithtrix MCP server expose? +

43 tools across 4 categories: Destructive, Execute, Read, Write. 19 are read-only. 24 can modify, create, or delete data.

How do I enforce a policy on Lithtrix? +

Register the Lithtrix 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 Lithtrix tool call.

Deterministic rules across all 43 Lithtrix tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON LITHTRIX →

Instant setup, no code required.

43 Lithtrix tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Lithtrix's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →