Skip to main content
Glama
Sign In
agent-discussion-mcp

agent-discussion-mcp

by ewanni
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
API_AGENT_DBNoLegacy fallback for AGENT_DISCUSSION_DB
API_AGENT_MODELNoLegacy fallback for AGENT_DISCUSSION_MODEL
API_AGENT_API_KEYNoLegacy fallback for AGENT_DISCUSSION_API_KEY
API_AGENT_TIMEOUTNoLegacy fallback for AGENT_DISCUSSION_TIMEOUT
API_AGENT_BASE_URLNoLegacy fallback for AGENT_DISCUSSION_BASE_URL
AGENT_DISCUSSION_DBNoSQLite database path for profiles and session audit events~/.agent_discussion_mcp/data.db
AGENT_DISCUSSION_MODELNoDefault model for agents without custom overridegpt-4o-mini
AGENT_DISCUSSION_API_KEYNoAPI key for OpenAI-compatible endpoint
AGENT_DISCUSSION_TIMEOUTNoHTTP request timeout in seconds120
AGENT_DISCUSSION_BASE_URLNoBase URL for /chat/completionshttps://api.openai.com/v1

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
create_agentC

Create a reusable profile. Provider endpoint and API key are server-wide.

update_agentB

Update fields on an existing profile; omitted fields remain unchanged.

list_agentsB

List profiles without exposing system prompts or secrets.

run_soloB

Run one agent to execute a task.

If working_dir (or workspace_path) is provided, the agent receives full workspace tools (file inspection, edits, and shell command execution) to autonomously accomplish the task. Includes periodic heartbeat progress reporting and inactivity watchdog protection.

run_discussionA

Run a bounded multi-agent discussion with an independent judge.

Provide at least two participant names. judge may be omitted when a profile with role judge exists. The token limit applies to generated completion tokens across the entire discussion.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.2/5.0

Scored across 5 tools

Disambiguation5/5

Each tool targets a distinct action on a clearly identified resource: profile CRUD (create/update/list) versus execution (run_solo for one agent, run_discussion for multi-agent with a judge). The descriptions clearly delineate the two execution modes, so there is little risk of misselection.

Naming Consistency4/5

Names follow a mostly consistent verb_noun pattern (create_agent, update_agent, run_solo, run_discussion). The only minor deviation is plural 'list_agents' versus singular elsewhere, but the convention remains predictable and readable.

Tool Count4/5

Five tools is slightly lean for a profile-management plus execution server, but each tool earns its place covering profile lifecycle and both single- and multi-agent runs. Nothing appears redundant or padded.

Completeness3/5

The profile lifecycle lacks delete and get/read-single operations, so an agent can create, update, and list profiles but cannot remove or fetch one specifically. Execution paths are covered, but the CRUD surface has a notable gap.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues

Resources