Skip to main content
Glama

Connect GitHub

project_github_connect

Connect or replace a local GitHub credential through GitHub Device Flow, so users authorize at github.com and tokens stay in the encrypted vault instead of being pasted into chat.

Instructions

Connect GitHub through its Device Flow. The user authorizes at github.com; access and refresh tokens are saved in the encrypted local vault and are never returned. Use when: the user wants to connect or replace the local GitHub credential without pasting a token into chat. Avoid when: the user only needs GitHub public read access or has already configured a token. Speed: start returns a short-lived verification code; poll only at the interval GitHub specifies. Output: github_connect: start returns verification_uri, user_code, pending_id and expiry; poll returns pending, denied, expired or connected (never a token). Batch-safe: no

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": "project_github_connect"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
pending_idNoaction=poll: opaque id returned by action=start; it does not contain the device code or token.
replace_existingNoaction=start: 1 explicitly authorizes replacing an existing GitHub credential; 0 does not.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.13.0

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare openWorldHint=true and destructiveHint=false; the description adds real context on top: tokens go to an encrypted local vault and are never returned, and start yields only a short-lived verification code. It also pre-empts the destructive-looking replace_existing=1 path by requiring explicit authorization, avoiding any annotation contradiction.

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?

Labeled one-liners (Use when / Avoid when / Speed / Output / Batch-safe) front-load the routing decision and keep polling discipline visible. Every line carries information not already in annotations or schema; nothing is repeated verbatim.

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?

With no output schema, the description correctly substitutes by enumerating start and poll return values and stating that no token is ever returned. Minor gaps remain: the default value of replace_existing and the recovery step after 'expired'/'denied' are not stated.

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

Parameters5/5

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

The 'Speed' and 'Output' lines map directly onto the two-state action enum, telling the agent what start does and that poll must be paced at GitHub's interval. The 'Use when'/'replace_existing' pairing plus the vault note clarifies the semantics of the 0/1 replacement flag beyond the schema wording.

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 and resource ('Connect GitHub') plus the mechanism ('through its Device Flow'), which no sibling tool offers. It also distinguishes this credential-shaping operation from the many read/write file and CI siblings by naming the outcome (a locally vaulted credential).

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

Usage Guidelines5/5

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

Explicit 'Use when' clause (connecting or replacing the local GitHub credential without pasting a token into chat) and an explicit 'Avoid when' clause (public read access only, or token already configured). This is the highest form of routing guidance an agent can get.

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