Skip to main content
Glama

overleaf_configure_auth

Stores Overleaf session cookies, Git Bridge tokens, and self-hosted host URLs locally with restricted file permissions to authenticate AI coding agents.

Instructions

Save Overleaf session cookie, Git Bridge token, or self-hosted host URL locally (mode 0600).

Args: cookie: Either 'browser' (auto-read from Chrome/Firefox), a full Cookie header string, or the value of 'overleaf_session2' from browser DevTools. git_token: Overleaf Git integration token (from Overleaf Account Settings -> Git Integration). host: Overleaf web host (default: 'www.overleaf.com', or your self-hosted domain). git_host: Overleaf Git host (default: 'git.overleaf.com').

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "overleaf_configure_auth"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostNo
cookieNo
git_hostNo
git_tokenNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations present, the description carries the full disclosure burden and does add real behavior: credentials are persisted locally with mode 0600, and 'browser' triggers automatic reading from Chrome/Firefox. It does not state whether existing stored credentials are overwritten, whether the session/token is validated against Overleaf before saving, or what occurs on invalid input, which are the key traits for a credential-writing 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?

Front-loaded one-sentence summary followed by a scannable per-argument breakdown with no filler. The Args-list framing is slightly docstring-like but the content is tight and every line carries information an agent needs.

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 four-parameter credential-setup tool with an output schema, the argument documentation is solid and return values need not be explained. However, with zero annotations the description should also cover persistence/overwrite semantics and whether saving validates the credential, which is the main thing an agent needs to sequence this correctly.

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

Parameters4/5

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

Schema coverage is 0%, so the description must compensate, and it largely does: it defines the three accepted forms of 'cookie' (including the special literal 'browser', which the schema does not express), the origin of git_token in Overleaf account settings, and the default hosts for both host and git_host. Minor gap: the schema lists null defaults while the description asserts concrete defaults, leaving the null-versus-default relationship unstated.

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?

The opening sentence pairs a specific verb ('Save') with three concrete credential resources (session cookie, Git Bridge token, host URL) and adds the storage detail (locally, mode 0600). That is enough to tell it apart from a status-check tool like overleaf_auth_status, but no sibling is named or explicitly ruled out, so it stops short of a 5.

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?

Usage is only implied: an agent can infer this must be called before cookie/token-dependent operations, and the per-argument notes hint at when each credential is needed. There is no explicit statement of when to call this versus overleaf_auth_status, no prerequisite ordering, and no note about re-running or overwriting existing config.

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