// SCAN REPORT

TOOL4LM

22 tools. 4 can modify or destroy data without limits.

4 write tools that can modify data. Rate limits recommended.

Last updated: 1 Jul 2026

4 can modify or destroy data

18 read-only

22 tools total

Community server · catalogue entry verified 01/07/2026

How to control TOOL4LM ↓

TOOL MAP

What TOOL4LM exposes to your agents

Read (18) Write / Execute (4) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous TOOL4LM tools

Execute · Medium index_build Building an index is an active operation that processes data and creates new structures, going beyond simple reads. Execute · Medium index.build Building a search index is not a simple read; it processes documents and writes index data structures to storage. Execute · High calc_eval A calculator 'eval' function typically executes expression evaluation, which depending on implementation could run arbitrary code. Execute · Medium calc.eval Evaluating arbitrary math expressions constitutes code/expression execution.

4 of TOOL4LM's 22 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control TOOL4LM

PolicyLayer is an MCP gateway — it sits between your AI agents and TOOL4LM, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations

{
  "doc_find": {
    "limits": [
      {
        "counter": "doc_find_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 TOOL4LM — 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 TOOL4LM →

Instant setup, no code required.

FULL CATALOGUE

All 22 TOOL4LM tools

EXECUTE 4 tools

Execute calc_eval Alias of calc.eval Execute calc.eval Evaluate math expression (no external calls). Execute index_build Alias of index.build Execute index.build Build MiniSearch index for documents in sandbox directory.

READ 18 tools

Read doc_find Alias of doc.find Read doc_read Alias of doc.read Read doc.find Search local documents within sandbox directory. Builds index if missing. Read doc.read Read a file from sandbox directory (text or pdf). Read sch_get Alias of sch.get Read sch_search Alias of sch.search Read sch.get Get scholarly metadata by DOI/arXivId/URL. Read sch.search Academic-first search (arXiv + Crossref + Wikipedia). Read web_fetch Alias of web.fetch Read web_read Alias of web.read Read web_search Alias of web.search Read web.fetch Fetch a URL with size/time limits and anti-SSRF. Read web.read Extract readable content from given HTML (or pass html from web.fetch). Read web.search Multi-engine web search (SearXNG + DuckDuckGo HTML). Read wiki_get Alias of wiki.get Read wiki_search Alias of wiki.search Read wiki.get Wikipedia summary by title. Read wiki.search Wikipedia title search (public API).

EXPLORE

Related servers

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

FAQ

Questions about TOOL4LM

Is the TOOL4LM MCP server safe to use without restrictions? +

The TOOL4LM server is primarily read-only with 18 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the TOOL4LM MCP server expose? +

22 tools across 2 categories: Execute, Read. 18 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on TOOL4LM? +

Register the TOOL4LM 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 TOOL4LM tool call.

Deterministic rules across all 22 TOOL4LM tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TOOL4LM →

Instant setup, no code required.

22 TOOL4LM tools catalogued and risk-classified — across an index of 43,000+ MCP servers.