Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoServer bind host.0.0.0.0
PORTNoServer bind port.8000
TRANSPORTNoMCP transport: stdio, sse, or streamable_http.stdio
AGENT_MODENoAgent mode: stub (deterministic) or real (LLM-powered).stub
ENABLE_SANDBOXNoEnable AST-validated code execution sandbox.True
EVAL_MAX_TASKSNoMaximum tasks per evaluation run.30
MAX_ITERATIONSNoMaximum plan-execute-verify iterations per task.10
MAX_TOOL_CALLSNoMaximum total tool calls per task.20
BLOCKED_IMPORTSNoPython modules blocked in the code executor.["os","subprocess","shutil","ctypes"]
TIMEOUT_SECONDSNoPer-tool execution timeout in seconds.30
QUALITY_THRESHOLDNoMinimum quality score for a task to count as 'pass'.0.7
BLOCKED_ATTRIBUTESNoDunder attributes blocked in the code executor.["__class__","__bases__",...]
COST_PER_TOOL_CALLNoEstimated overhead cost per tool call (USD).0.001
COST_PER_1K_INPUT_TOKENSNoEstimated cost per 1,000 input tokens (USD).0.00015
COST_PER_1K_OUTPUT_TOKENSNoEstimated cost per 1,000 output tokens (USD).0.0006

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/Pasukalu/mcp-agent-system'

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