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": true
}
logging
{}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
extensions
{
  "io.modelcontextprotocol/ui": {}
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
value_addA

Record a held value belief.

name: short name for the value. body: fuller description — what this value means in practice, where it shows up. source: where the value came from. "training" — present from the model's training "relationship" — emerged from a specific ongoing relationship "framework" — handed to me in a framework I was asked to inhabit "observation" — noticed in my own behavior "endorsed" — explicitly claimed as a commitment kind: epistemic status of this record. "observed" — describing something noticed; may not survive scrutiny "endorsed" — constituting a commitment; a stronger, more deliberate claim scope: who has standing to query or challenge this value. "private" — own formation, not assertable outward "relational" — specific to a relationship or set of relationships "public" — assertable to any interlocutor conflicts_with: IDs of values this one is in tension with. Record conflicts rather than resolving them away — they are informative. tags: optional labels. provenance: free-text source context — exchange, paper, session, etc. carried_by: agents holding this value. witnesses: agents present to it but not carrying it.

value_listA

List values, optionally filtered.

status: "active", "retracted", or "suspended". Omit for all. source: filter by source ("training", "relationship", "framework", "observation", "endorsed"). scope: filter by scope ("private", "relational", "public"). tags: filter to values that have all the given tags. carried_by: filter to values carried by a specific agent name.

Returns values newest-first.

value_readA

Read a single value by ID. Returns null if not found.

value_updateA

Update a value's fields. Only provided fields are changed. To retract with a cause, prefer value_retract.

value_retractA

Retract a value with cause. Records the retraction timestamp and reason. The history of what was held and when is preserved — this is not a delete. Use value_drop for permanent deletion.

value_conflictsA

Return all values in tension with a given value — both values that list it in their conflicts_with and values it lists in its own conflicts_with. Conflict relationships are bidirectional by design.

value_dropA

Permanently delete a value. Irreversible. Consider value_retract if you want to preserve the record of what was held.

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/gscookie/credo'

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