// SCAN REPORT

OpenCode MCP Server

5 tools. 2 can modify or destroy data without limits.

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

Last updated: 12 Jun 2026

2 can modify or destroy data

3 read-only

5 tools total

Community server · catalogue entry verified 12/06/2026

How to control OpenCode MCP Server ↓

TOOL MAP

What OpenCode MCP Server exposes to your agents

Read (3) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous OpenCode MCP Server tools

Write · High configure_context7 This tool creates or modifies configuration state (enabling/disabling features) and stores sensitive credentials (API keys), which are reversible but consequential changes. Write · Medium learn_context This tool writes/stores data (preferences, rules, context) into persistent memory for future retrieval.

2 of OpenCode MCP Server's 5 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control OpenCode MCP Server

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

Rate limit write operations

{
  "learn_context": {
    "limits": [
      {
        "counter": "learn_context_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "index_codebase": {
    "limits": [
      {
        "counter": "index_codebase_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 OpenCode MCP Server — 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 OPENCODE →

Free to start. No card required.

FULL CATALOGUE

All 5 OpenCode MCP Server tools

WRITE 2 tools

Write learn_context Memorizes important information (preference, technical rule, context) for future use. Write configure_context7 Configures the Context7 integration dynamically. Allows enabling/disabling real-time documentation retrieval a

READ 3 tools

Read index_codebase Performs a deep scan of the project structure and key files to populate semantic memory. Read refine_prompt Refines a prompt using local semantic memory, a local AI model for rewriting, and real-time external documenta Read search_memory Searches the semantic memory for specific information without refining a prompt.

FAQ

Questions about OpenCode MCP Server

How do I prevent bulk modifications through OpenCode MCP Server? +

The OpenCode MCP Server server has 2 write tools including learn_context, configure_context7. 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 OpenCode MCP Server.

How many tools does the OpenCode MCP Server MCP server expose? +

5 tools across 2 categories: Read, Write. 3 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on OpenCode MCP Server? +

Register the OpenCode MCP Server 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 OpenCode MCP Server tool call.

Deterministic rules across all 5 OpenCode MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON OPENCODE →

Free to start. No card required.

5 OpenCode MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.