// SCAN REPORT

Ts

40 tools. 7 can modify or destroy data without limits.

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

Last updated: 29 Jun 2026

7 can modify or destroy data

33 read-only

40 tools total

Community server · catalogue entry verified 29/06/2026

How to control Ts ↓

TOOL MAP

What Ts exposes to your agents

Read (33) Write / Execute (6) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Ts tools

Destructive · High organizeImports Sort, coalesce, and remove unused imports in a TypeScript/JavaScript file. Uses TypeScript Write · Medium docCommentTemplate Generate a JSDoc comment template for a function, method, or class at a position. Returns the template text with @param, @returns, etc. base Write · Medium documentHighlights Find all occurrences of a symbol within a file (or set of files). Distinguishes between read and write references. More efficient than find_ Write · Medium inferReturnType Add an explicit return type annotation to a function, inferred by TypeScript. Position must be on the function name or declaration keyword.

7 of Ts's 40 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Ts

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

Deny destructive operations

{
  "organizeImports": {
    "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

{
  "docCommentTemplate": {
    "limits": [
      {
        "counter": "doccommenttemplate_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "completionEntryDetails": {
    "limits": [
      {
        "counter": "completionentrydetails_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 Ts — 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 TS →

Instant setup, no code required.

FULL CATALOGUE

All 40 Ts tools

DESTRUCTIVE 1 tools

Destructive organizeImports Sort, coalesce, and remove unused imports in a TypeScript/JavaScript file. Uses TypeScript

WRITE 6 tools

Write docCommentTemplate Generate a JSDoc comment template for a function, method, or class at a position. Returns the template text wi Write documentHighlights Find all occurrences of a symbol within a file (or set of files). Distinguishes between read and write referen Write inferReturnType Add an explicit return type annotation to a function, inferred by TypeScript. Position must be on the function Write moveSymbol Move top-level declarations (functions, classes, types, constants) to another file. Automatically rewires all Write rename Rename a TypeScript/JavaScript symbol (variable, function, class, type, property, etc.) and update all referen Write typeDefinition Navigates to the type

READ 33 tools

Read completionEntryDetails Get full details for specific completion entries. Follow-up to completion_info for richer information includin Read completionInfo Get autocomplete suggestions at a position. Returns all possible completions with their kinds, sort text, and Read definition Returns the file location(s) where a symbol is defined. The fundamental Read definitionAndBoundSpan Like Read extractConstant Extract the selected expression into a named constant. TypeScript infers the type. The response includes renam Read extractFunction Extract the selected code range into a new function. TypeScript auto-detects parameters and return type. The r Read extractType Extract an inline type annotation into a named type alias. Select the type span to extract. The response inclu Read fileReferences Finds every file that imports or references a given file. The reverse dependency graph for a single file. Read findSourceDefinition Navigate to the actual TypeScript source instead of .d.ts declaration files. Useful when working with librarie Read format Format a range of code according to TypeScript Read getApplicableRefactors Discover what refactorings are available at a position or selection. Use before attempting a refactor to see w Read getCodeFixes Get available code fixes for specific error codes at a range in a TypeScript/JavaScript file. Returns the raw Read getCombinedCodeFix Get a combined code fix that applies all instances of a fix across a file in one action. For example, Read getDiagnostics Get all errors, warnings, and suggestions for a TypeScript/JavaScript file. Reports type errors, unused variab Read getEditsForFileRename Rename or move a TypeScript/JavaScript file OR folder and automatically update all import paths across the pro Read getMoveToRefactoringFileSuggestions Get suggested target files when moving a symbol to another file. Returns both a suggested new file name and ex Read getOutliningSpans Get code folding regions for a file. Returns the hierarchical structure of code blocks including their kinds ( Read getSupportedCodeFixes Returns the list of all error codes that have available code fixes. Read implementation Finds concrete implementations of an interface or abstract class. Given an interface Read inlineVariable Inline a variable — replace all references with the variable Read mapCode Map/insert/replace code snippets into a file. Designed for AI code generation workflows. How matching works: Read navto Workspace-wide symbol search by name. Takes a search string and returns matching symbols across all project fi Read navtree Get the complete hierarchical structure of a file — all classes, functions, variables, interfaces, type aliase Read prepareCallHierarchy Returns the call hierarchy item(s) at a position — the entry point for call hierarchy queries. Returns the fun Read projectInfo Returns the tsconfig.json path, the full list of files in the project, and whether the language service is act Read provideCallHierarchyIncomingCalls Returns all functions/methods that call the function at the given position. Answers Read provideCallHierarchyOutgoingCalls Returns all functions/methods that the function at the given position calls. Answers Read provideInlayHints Get inlay hints (inline type annotations) for a range. Shows inferred types, parameter names at call sites, an Read quickinfo Get type information, documentation, and JSDoc tags for a symbol at a position. Returns the hover info — kind, Read references Find all usages of a symbol across the project. Provide the file path and 1-based line/offset of any occurrenc Read selectionRange Get semantically meaningful selection ranges for smart expand/shrink selection. Returns nested spans that repr Read signatureHelp Get function/method signature information at a call site. Returns parameter names, types, and documentation fo Read todoComments Find all TODO, FIXME, HACK, and other configured comment markers in a file. Returns the location and text of e

EXPLORE

Related servers

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

FAQ

Questions about Ts

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

Yes. The Ts server exposes 1 destructive tools including organizeImports. 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 Ts? +

The Ts server has 6 write tools including docCommentTemplate, documentHighlights, inferReturnType. 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 Ts.

How many tools does the Ts MCP server expose? +

40 tools across 3 categories: Destructive, Read, Write. 33 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Ts? +

Register the Ts 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 Ts tool call.

Deterministic rules across all 40 Ts tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TS →

Instant setup, no code required.

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