Skip to main content
Glama

Recursive Companion MCP

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
AWS_REGIONNoAWS region for Bedrock accessus-east-1
MAX_ITERATIONSNoMaximum refinement iterations5
REQUEST_TIMEOUTNoTimeout in seconds600
BEDROCK_MODEL_IDNoMain generation modelanthropic.claude-3-sonnet-20240229-v1:0
AWS_ACCESS_KEY_IDYesYour AWS access key ID
CRITIQUE_MODEL_IDNoModel for critiques (use Haiku for speed)anthropic.claude-3-haiku-20240307-v1:0
PARALLEL_CRITIQUESNoNumber of parallel critiques per iteration2
AWS_SECRET_ACCESS_KEYYesYour AWS secret access key
CONVERGENCE_THRESHOLDNoSimilarity threshold for convergence (0.90-0.99)0.95

Schema

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

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/democratize-technology/recursive-companion-mcp'

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