Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GITHUB_TOKENNoGitHub personal access token (optional, increases rate limit to 5,000/hr).
MOLTBOOK_API_KEYNoRequired for Moltbook adapter.
AGENTSCORE_ADAPTERNoChoose the data source adapter: demo, github, json, or moltbook.demo
AGENTSCORE_ENFORCENoIf true, policy gate can block risky results.false
AGENTSCORE_AUDIT_LOGNoSet false to suppress structured policy audit events.auto
AGENTSCORE_CACHE_TTLNoScore cache TTL in seconds.86400
AGENTSCORE_DATA_PATHNoRequired for JSON adapter. Path to JSON data file.
AGENTSCORE_HTTP_HOSTNoBind host for HTTP transport.127.0.0.1
AGENTSCORE_HTTP_PATHNoMCP endpoint path for HTTP transport./mcp
AGENTSCORE_HTTP_PORTNoBind port for HTTP transport.8787
AGENTSCORE_TRANSPORTNoTransport mode: stdio or http (Streamable HTTP server mode).stdio
AGENTSCORE_AUDIT_TOKENNoOptional bearer token required for policy/audit endpoints.
AGENTSCORE_PUBLIC_MODENoIf true, requires explicit adapter and blocks demo mode.false
AGENTSCORE_ENABLED_TOOLSNoComma-separated tool allow-list (agentscore, sweep, xray).agentscore,sweep,xray
AGENTSCORE_RATE_LIMIT_MSNoMoltbook adapter request delay in milliseconds.200
AGENTSCORE_HTTP_AUTH_TOKENNoOptional bearer token required for /mcp HTTP endpoint.
AGENTSCORE_POLICY_MIN_SCORENoMinimum allowed score when policy is enforced.550
AGENTSCORE_AUDIT_MAX_ENTRIESNoIn-memory cap for retained policy audit events.500
AGENTSCORE_POLICY_BLOCK_FLAGSNoComma-separated flag substrings that trigger blocking.prompt injection,manipulation keyword,account not claimed
AGENTSCORE_POLICY_FAIL_ON_ERRORSNoIf true, any per-handle scoring errors trigger blocking.false
AGENTSCORE_POLICY_TRUSTED_ADAPTERSNoComma-separated adapters allowed in enforced mode.github,json,moltbook
AGENTSCORE_POLICY_BLOCK_THREAT_LEVELSNoComma-separated blocked sweep levels (SUSPICIOUS, COMPROMISED).COMPROMISED
AGENTSCORE_POLICY_BLOCK_RECOMMENDATIONSNoComma-separated blocked recommendations (TRUST, CAUTION, AVOID).AVOID

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

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/tmishra-sp/agentscore-mcp'

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