Skip to main content
Glama
ni-c

woodpecker-ci-mcp

by ni-c

Add a forge

create_forge

Register an additional forge for authentication, requiring an existing OAuth application and admin privileges. Use this to add a new code hosting service to Woodpecker.

Instructions

Registers an additional forge. Admin only, and two-step: a forge is a way to sign in, and Woodpecker grants administrator rights by login name alone, so an account on the new forge spelled like an admin is one. The OAuth application has to exist on the forge side first, with this Woodpecker as its callback.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesBase URL of the forge, e.g. "https://github.com".
typeYesWhich forge software this is.
clientYesOAuth client id from the forge.
oauth_hostNoPublic URL used for the OAuth redirect, when it differs from "url" — the usual case for a forge reachable under two names.
skip_verifyNoSkip TLS verification towards this forge. Only for a private CA you cannot install; it disables certificate checking entirely.
confirm_tokenNoToken from a previous call of this tool.
oauth_client_secretYesOAuth client secret. Write-only — Woodpecker never returns it again.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
truncatedNoPresent only when the answer was shortened to fit the budget.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.3.1
    • addedInput schema / properties / confirm_token
      Added value: +{
      +  "description": "Token from a previous call of this tool.",
      +  "pattern": "^[0-9a-f]{32}$",
      +  "type": "string"
      +}
  2. First observedv0.2.0

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond basic annotations: warns that admin rights are granted by login name alone, notes the security implication for new forge accounts, and explains the two-step nature plus prerequisite callback setup; no contradiction with non-read-only annotations.

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?

Purpose is front-loaded and every sentence carries essential information (security warning, prerequisite, flow); no filler or redundancy.

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?

Covers the key context: admin permission, two-step flow, OAuth prerequisite, and security risk; it does not explicitly spell out that the first call returns a token to be used with confirm_token, but the schema parameter makes this recoverable.

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 already covers all 7 parameters with meaningful descriptions (including write-only secret, TLS skip, confirm_token); description does not need to add parameter detail, so baseline 3 applies.

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?

Begins with 'Registers an additional forge', naming the action and object precisely and distinguishing it from update/delete/list forge siblings; 'additional' clarifies create semantics.

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

Usage Guidelines4/5

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

States admin-only restriction, the two-step registration flow, and the prerequisite OAuth app/callback setup; however it does not explicitly name update_forge as the alternative for modifying an existing forge.

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