// SCAN REPORT

MCP Context Manager

21 tools. 6 can modify or destroy data without limits.

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

Last updated:

6 can modify or destroy data
15 read-only
21 tools total

Community server · catalogue entry verified 12/06/2026

How to control MCP Context Manager ↓

TOOL MAP

What MCP Context Manager exposes to your agents

Read (15) Write / Execute (4) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS
Critical Risk

The most dangerous MCP Context Manager tools

Destructive · Medium clear_cache Clearing a cache is a non-reversible deletion of stored index data. Destructive · High delete_symbol This tool irreversibly deletes code artifacts (functions, classes, symbols) from the codebase. Execute · Medium build_dependency_graph This tool triggers a processing/analysis operation across the entire codebase to construct and store a dependency graph. Execute · Medium index_repository Indexing a repository involves scanning the filesystem, parsing code files, building data structures, and writing cache/index files.

6 of MCP Context Manager'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 MCP Context Manager

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

Deny destructive operations
{
  "clear_cache": {
    "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
{
  "insert_after_symbol": {
    "limits": [
      {
        "counter": "insert_after_symbol_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "find_similar": {
    "limits": [
      {
        "counter": "find_similar_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register MCP Context Manager — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON MCP CONTEXT MANAGER →

Free to start. No card required.

FULL CATALOGUE

All 21 MCP Context Manager tools

DESTRUCTIVE 2 tools
Destructive clear_cache Clear the cached index for a repository. Useful if cache becomes corrupted or you want to force a fresh index. Destructive delete_symbol 🗑️ NEW: Delete a symbol (Serena-inspired). Remove function/class/etc cleanly. Symbol-level deletion. Use for
EXECUTE 2 tools
Execute build_dependency_graph 🚀 NEW: Build dependency graph for the entire codebase. Call this once after indexing to enable smart context Execute index_repository 🔧 REQUIRED FIRST STEP: Index or re-index the repository to enable all context-manager tools. Uses cached inde
WRITE 2 tools
Write insert_after_symbol ✏️ NEW: Insert code after a symbol (Serena-inspired). Symbol-level editing without reading full files. Precise Write replace_symbol ✏️ NEW: Replace a symbol with new code (Serena-inspired). Surgical precision editing. Replaces entire symbol d
READ 15 tools
Read find_similar Find code similar to a given symbol. Useful for discovering related implementations, similar patterns, or alte Read find_symbol ⭐ PREFERRED FOR SYMBOLS: Use this INSTEAD OF Grep when looking for specific functions, classes, or variables. Read find_symbol_references 🔍 NEW: Find all places where a symbol is used (Serena-inspired). Shows usages across all files with context. Read get_class ⭐ PREFERRED OVER Read: Get class definition without reading the entire file. Optionally filter specific method Read get_dependencies Find all dependencies (imports/requires) for a file or symbol. Useful for understanding what code needs. Read get_dependency_tree 🚀 NEW: Dependency-aware context. Visualize and retrieve dependency tree for a symbol. Shows what code depends Read get_file_summary ⭐ PREFERRED FOR FILE OVERVIEW: Get file structure (exports, functions, classes, imports) without reading full Read get_function ⭐ PREFERRED OVER Read: Get complete function code without reading the entire file. Saves 85% tokens compared t Read get_function_with_context 🚀 NEW: Smart context expansion. Get a function WITH its type definitions and immediate dependencies (signatur Read get_related_symbols 🔗 NEW: Find symbols related to a given symbol. Discovers related code by file proximity, name similarity, and Read get_relevant_context ⭐ PREFERRED SEARCH: Use this INSTEAD OF Grep for finding code by description. Natural language search with BM2 Read get_repository_structure ⭐ PREFERRED OVER ls/tree: Get clean repository structure showing directories and file types. Use this INSTEAD Read get_usage_stats View token usage statistics for this session. Shows how many tokens each MCP tool used vs what full file reads Read index_git_changes 🚀 NEW: Git-aware incremental indexing. Only indexes files changed since a git ref (branch/commit). MUCH FASTE Read search_code ⭐ PREFERRED OVER Grep: Search for code patterns with regex support. Returns ranked results with minimal contex
EXPLORE

Related servers

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

Sperax Ecosystem Crypto & DeFI MCP Server 1318 tools
adminautomation
Mcp Afip 1300 tools
adminautomation
Mcp Ap2 1300 tools
adminautomation
BNB Chain MCP 1240 tools
adminautomation
Nodebench 824 tools
adminautomation
Amazon Bedrock Knowledge Base Retrieval MCP Server 805 tools
adminautomation
Amazon Data Processing MCP Server 805 tools
adminautomation
Amazon ECS MCP Server 805 tools
adminautomation
FAQ

Questions about MCP Context Manager

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

Yes. The MCP Context Manager server exposes 2 destructive tools including clear_cache, delete_symbol. 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 MCP Context Manager? +

The MCP Context Manager server has 2 write tools including insert_after_symbol, replace_symbol. 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 MCP Context Manager.

How many tools does the MCP Context Manager MCP server expose? +

21 tools across 4 categories: Destructive, Execute, Read, Write. 15 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on MCP Context Manager? +

Register the MCP Context Manager 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 MCP Context Manager tool call.

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

ENFORCE POLICY ON MCP CONTEXT MANAGER →

Free to start. No card required.

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

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.