Skip to main content
Glama

OpenCode MCP servers

opencode_mcp

Inspect and manage the MCP servers an OpenCode project uses: list servers and status, view resource catalogs, add local or remote servers, remove, connect, or disconnect them.

Instructions

Inspect and manage the MCP servers that OpenCode itself uses (not this bridge). Actions: list (servers + connection status), resources (tool/resource catalog), add (local or remote), remove, connect, disconnect. Server enablement is global per OpenCode project; per-session tool filtering is done with session permissions.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "opencode_mcp"
  }
}

Input Schema

NameRequiredDescriptionDefault
typesNoResource types for action=resources
actionYes
configNoServer config for action=add
serverNoServer name, for add/remove/connect/disconnect
directoryNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only supply readOnlyHint=false, so the description carries most of the burden. It usefully discloses scope (OpenCode's own servers, not the bridge), global enablement semantics, and that add supports local or remote configs — but says nothing about what remove destroys, whether connect requires an existing server entry, or whether changes take effect immediately or need a restart.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences: identity/scope first, then actions, then the enablement caveat. No filler, and the most important disambiguation ('not this bridge') is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-action tool with no output schema and only 60% schema description coverage, the definition covers what list and resources return but leaves the mutating actions underspecified — no indication of failure modes, permission requirements, or per-action parameter pairing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 60%, and the description maps the action enum values to behavior and tags 'server' as the name used by add/remove/connect/disconnect, plus hints that 'types' filters the resources catalog. But action-specific requirements (config only for add, server only for remove/connect/disconnect) and the 'directory' parameter are left entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Inspect and manage the MCP servers that OpenCode itself uses') and immediately disambiguates from the bridge's own servers. The enumerated action list (list, resources, add, remove, connect, disconnect) makes the tool's surface concrete and distinguishable from siblings like opencode_configure.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The note that 'server enablement is global per OpenCode project; per-session tool filtering is done with session permissions' is a genuine routing hint away from this tool for per-session scoping. However, there is no guidance per action (e.g., when to use connect vs add vs list), and no stated prerequisites for remove or connect.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.