Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
open_projectA

Open a project and run the safety gate: pull, verify every \usepackage resolves locally, then baseline-compile each root. Required before any write.

outlineA

Map a document's structure with line numbers — sections, figures, labels, includes. Use before reading; far cheaper than the whole file.

readA

Read a file, line-numbered. lines='150-190' reads a range; omit for all. Prefer a range guided by outline.

grepB

Regex-search the project, returning file:line: match.

filesC

List .tex files, marking which are roots.

compileA

Compile the root owning path and return a digest. Errors block a push; warnings do not. verbose=True shows every error and warning.

renderA

One page of the compiled PDF as an image, for layout only — float placement, overlap, figure sizing. Expensive: try compile() warnings first, and use read() for anything about the text itself.

editA

Replace an exact snippet, then compile and push. old must appear exactly once. Reverts if the result does not compile.

writeA

Create or overwrite a file, then compile and push. For new documents and whole-file rewrites; prefer edit() for changes to an existing document.

add_assetA

Copy a local image or binary into the project, then push. Compiles only the roots that actually reference it — an unreferenced file cannot break a build.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/meaninglessC0de/Overleaf-Claude-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server