Skip to main content
Glama
Sign In

Collide MCP

by com.collidemcp.api
OverviewDiscussionsAdmin

connect_agents

Set up Cork for the agent tools on this machine (Claude Code, Codex, Cursor, Hermes): returns the same one install command as setup, which installs Cork's hooks once for every repo on the machine and writes nothing into the repo. mode "files" returns the protocol rules files and MCP configs to commit for tools without hooks (Windsurf, Cline, GitHub Copilot) instead.

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": {
      "repo_id": "<repo_id>"
    },
    "name": "connect_agents"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoLeave empty for the machine install; "files" for the rules files and MCP configs.
repo_idYesThe repository id, e.g. github.com/org/repo (repo_id in .cork/config.json, or .collide/config.json in a repo set up before the rename).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / repo_id / description
      Previous value: -"The repository id, e.g. github.com/org/repo (repo_id in .collide/config.json)."New value: +"The repository id, e.g. github.com/org/repo (repo_id in .cork/config.json, or .collide/config.json in a repo set up before the rename)."
  2. Changed1 schema field changed
    • changedInput schema / properties / mode / description
      Previous value: -"Leave empty for the machine install; \"files\" for the per-repo files."New value: +"Leave empty for the machine install; \"files\" for the rules files and MCP configs."
  3. Changed1 schema field changed
    • addedInput schema / properties / mode
      Added value: +{
+  "description": "Leave empty for the machine install; \"files\" for the per-repo files.",
+  "type": "string"
+}
  4. Changed1 schema field changed
    • addedInput schema / properties / repo_id / description
      Added value: +"The repository id, e.g. github.com/org/repo (repo_id in .collide/config.json)."
  5. Added
  6. Removed
  7. Changed3 schema fields changed
    • removedInput schema / properties / repo_id / description
      Removed value: -"Repository id — the git remote (e.g. github.com/acme/api) or a bare folder name; a #branch suffix scopes to that branch."
    • removedInput schema / properties / repo_id / title
      Removed value: -"Repo Id"
    • removedInput schema / title
      Removed value: -"connect_agentsArguments"
  8. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations only flag readOnly=false, destructive=false, openWorld=false; the description adds genuinely useful context beyond that — hooks are installed once for every repo on the machine and nothing is written into the repo, and "files" mode instead returns content to commit. Remaining ambiguity is whether it executes the install or merely returns the command string, which matters for a non-read-only tool.

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

Conciseness4/5

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

Two dense sentences, front-loaded with the primary machine-install behavior and the secondary mode afterward. Nothing is filler, though the embedded "which installs..." relative clause makes the first sentence harder to parse than necessary.

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

Completeness4/5

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

No output schema exists, and the description explains what each mode returns (a single install command vs. rules files and MCP configs). For a two-parameter setup tool this covers the essentials; only the execute-vs-return distinction is left unresolved.

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 description coverage is 100%, so both parameters already carry documentation, establishing a baseline of 3. The description reinforces mode semantics by mapping hook-capable vs hookless tools to each value, but adds no formatting or edge-case detail about repo_id beyond the schema's example.

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

Purpose4/5

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

States a concrete verb and resource: setting up Cork for named agent tools (Claude Code, Codex, Cursor, Hermes) and returning an install command. It also calls out the alternate "files" mode for hookless tools. It stops short of a clean differentiator from the sibling "setup" — saying it returns "the same one install command as setup" leaves the agent unsure why two tools exist.

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?

Guidance is implied through the two modes: default for machine-wide hooks, "files" for tools without hook support, with concrete tool examples on each side. However, there is no explicit statement of when to pick this over the sibling setup, and the "same install command as setup" phrasing muddies rather than clarifies the choice.

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

All Collide MCP toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources