Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
NEAR_NETWORKNoNEAR network to use: testnet or mainnet. Keep testnet for the demo.testnet
NEAR_RPC_URLNoRead-only NEAR RPC endpoint.https://test.rpc.fastnear.com
NEARAI_API_KEYNoEnables the NEAR AI Cloud classifier, attacker model and attestation. Leave empty to run with local heuristics only.
NEARAI_TIMEOUTNoTimeout in seconds for LLM and attestation calls.60
NEARAI_BASE_URLNoOpenAI-compatible NEAR AI Cloud gateway base URL.https://cloud-api.near.ai/v1
GUARDIAN_OFFLINENoSet to 1 to skip NEAR RPC/NearBlocks calls and use fixtures. Explicit NEAR AI calls still run when a key is set.0
NEARAI_ATTESTATIONNoSet to 0 to skip the gateway attestation call, for endpoints without /attestation/report.1
NEARBLOCKS_API_URLNoNearBlocks v3 base URL.https://api-testnet.nearblocks.io
NEARAI_VICTIM_MODELNoLLM victim model for the red team.openai/gpt-4.1-mini
GUARDIAN_DAILY_LIMITNoWrapper daily limit, in token units.200
NEARAI_ATTACKER_MODELNoRed-team payload generator model.deepseek-ai/DeepSeek-V4.1-Flash-1017-abliterated
NEARAI_CLASSIFIER_MODELNoPrompt-injection classifier model.Qwen/Qwen3.8-27B
GUARDIAN_MAX_SINGLE_PAYMENTNoWrapper single-payment limit, in token units.50
NEARAI_ATTESTATION_CACHE_SECONDSNoHow long one gateway attestation is reused per process.300

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

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