// SCAN REPORT

CornMCP

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

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

Last updated: 11 Jun 2026

6 can modify or destroy data

12 read-only

18 tools total

Community server · catalogue entry verified 11/06/2026

How to control CornMCP ↓

TOOL MAP

Read (12) Write / Execute (6) Destructive / Financial (0)

MOST DANGEROUS TOOLS

High Risk

Execute · High corn_cypher This tool executes Cypher queries against a graph database. Write · Medium corn_quality_report The tool submits (creates/writes) a quality report with scored dimensions. Write · Low corn_session_start This tool creates a new session record/state in the system. Write · Medium corn_knowledge_store This tool writes data to a shared knowledge base, creating or modifying entries.

6 of CornMCP's 18 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL CORNMCP

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

Rate limit write operations

{
  "corn_quality_report": {
    "limits": [
      {
        "counter": "corn_quality_report_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "corn_changes": {
    "limits": [
      {
        "counter": "corn_changes_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 CornMCP — 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 CORNMCP →

Free to start. No card required.

ALL 18 CORNMCP TOOLS

EXECUTE 1 tools

Execute corn_cypher Run Cypher queries against the code knowledge graph. Supports MATCH, RETURN, WHERE, ORDER BY.\nExample: MATCH

WRITE 5 tools

Write corn_quality_report Submit a quality report with 4-dimension scoring (Build, Regression, Standards, Traceability). Each dimension Write corn_session_start Start a new work session. Call this at the beginning of a task to enable session tracking, quality gates, and Write corn_knowledge_store Store a knowledge item in the shared knowledge base. Use for bug fixes, patterns, decisions, and conventions t Write corn_memory_store Store a memory for later recall. Agents remember across sessions. Include project and branch for scoped recall Write corn_session_end End the current work session. Provide a summary of changes and decisions for handoff.

READ 12 tools

Read corn_changes Check for recent code changes pushed by other agents/team members. Returns unseen commits and affected files. Read corn_code_context Get a 360° view of a code symbol: its methods, callers, callees, and related execution flows. Essential for ex Read corn_code_impact Analyze the blast radius of changing a specific symbol (function, class, file) to verify downstream impact bef Read corn_code_read Read raw source code from an indexed repository. Returns full file or a line range. Use after corn_code_search Read corn_code_search Search the codebase for architecture concepts, execution flows, and file matches using hybrid vector/AST searc Read corn_detect_changes Detect uncommitted changes and analyze their risk level. Shows changed symbols, affected processes, and risk a Read corn_health Check Corn Hub system health — services, uptime, version Read corn_knowledge_search Search the shared knowledge base semantically. Find bug fixes, patterns, decisions, and conventions contribute Read corn_list_repos List all indexed repositories with project ID mapping. Use this to find which projectId to pass to code tools. Read corn_memory_search Search agent memories by semantic similarity. Returns relevant memories from any agent. Read corn_tool_stats View Corn MCP tool usage analytics: success rates, latency, token estimates, and trends. Use to measure Corn e Read corn_plan_quality Assess the quality of a plan before execution. Scores against 8 criteria: clarity, scope, risks, testing, reve

RELATED SERVERS

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

FAQ

How do I prevent bulk modifications through CornMCP? +

The CornMCP server has 5 write tools including corn_quality_report, corn_session_start, corn_knowledge_store. 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 CornMCP.

How many tools does the Corn MCP server expose? +

18 tools across 3 categories: Execute, Read, Write. 12 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on CornMCP? +

Register the Corn 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 CornMCP tool call.

Deterministic rules across all 18 CornMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CORNMCP →

Free to start. No card required.

18 CornMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

CornMCP

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL CORNMCP

// ALL 18 CORNMCP TOOLS

// RELATED SERVERS

// FAQ