// SCAN REPORT

Syntax Map

21 tools. 3 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 2 Jul 2026

3 can modify or destroy data

18 read-only

21 tools total

Community server · catalogue entry verified 02/07/2026

How to control Syntax Map ↓

TOOL MAP

What Syntax Map exposes to your agents

Read (18) Write / Execute (2) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Syntax Map tools

Destructive · High clear_index This tool permanently removes the SQLite index file used for cross-file searches and caching. Execute · Medium run_query This tool executes tree-sitter queries, which are Turing-complete pattern-matching operations run against parsed source code. Write · Medium index_workspace This tool creates or updates a SQLite index database by scanning source files.

3 of Syntax Map's 21 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Syntax Map

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

Deny destructive operations

{
  "clear_index": {
    "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

{
  "index_workspace": {
    "limits": [
      {
        "counter": "index_workspace_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "build_context": {
    "limits": [
      {
        "counter": "build_context_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 Syntax Map — 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 SYNTAX MAP →

Instant setup, no code required.

FULL CATALOGUE

All 21 Syntax Map tools

DESTRUCTIVE 1 tools

Destructive clear_index Delete the SQLite workspace index file.

EXECUTE 1 tools

Execute run_query Run a tree-sitter query against one supported source file.

WRITE 1 tools

Write index_workspace Build or refresh the SQLite symbol index for all supported source files.

READ 18 tools

Read build_context Build markdown context for supported source files. Read find_definition Find symbol definitions by name across supported source files. Read find_indexed_definition Find exact symbol definitions from the SQLite workspace index with snippets. Read find_indexed_references Find identifier references from the SQLite workspace index with snippets. Read find_references Find identifier references by name across supported source files. Read get_ast_tree Return a depth-limited tree-sitter AST for one supported source file. Read get_index_status Return SQLite index path, indexed file count, symbol count, and stale file count. Read list_symbols List top-level symbols in one supported source file. Read lsp_completion Return workspace symbol completion items for the prefix before a zero-based LSP position. Read lsp_definition Return definition locations for the identifier at a zero-based LSP position. Read lsp_diagnostics Return lightweight syntax diagnostics from tree-sitter parse errors. Read lsp_document_symbols Return tree-sitter symbols converted to LSP DocumentSymbol ranges and kinds. Read lsp_hover Return markdown hover contents for the identifier at a zero-based LSP position. Read lsp_references Return reference locations for the identifier at a zero-based LSP position. Read lsp_signature_help Return signature help for the active call at a zero-based LSP position. Read lsp_workspace_symbols Return workspace symbols matching a case-insensitive query. Read search_symbols Search symbols from the SQLite workspace index. Read summarize_file Summarize language, line count, imports, exports, and symbols for one file.

EXPLORE

Related servers

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

FAQ

Questions about Syntax Map

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

Yes. The Syntax Map server exposes 1 destructive tools including clear_index. 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 Syntax Map? +

The Syntax Map server has 1 write tools including index_workspace. 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 Syntax Map.

How many tools does the Syntax Map MCP server expose? +

21 tools across 3 categories: Destructive, Execute, Read. 18 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Syntax Map? +

Register the Syntax Map 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 Syntax Map tool call.

Deterministic rules across all 21 Syntax Map tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SYNTAX MAP →

Instant setup, no code required.

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

// WHERE THIS COMES FROM

These policies come from Syntax Map'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 →