Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_HTTP_PORTNoThe port for the Streamable HTTP server (used in remote HTTP mode).
SYNOSMOSAI_AUDIT_LOGNoOptional audit log path. Append-only JSONL, off by default.

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
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
audit_evidence_chainB

生成 ISO/IEC 42001 + NIST AI RMF 可审计证据工件模板(六类:决策日志/风险登记册/模型卡/变更记录/人类监督证明/事件处置台账)——为 AI 系统准备可追溯审计证据链

a3_assessA

A³ 法则四维评分卡(意图/影响/可逆性/监督,各 1-5 分),返回总分(满分 20)与放行建议——AI 造/改 AI 或高影响动作发布前评估

passport_lookupC

查询技能/智能体身份码与溯源(本地台账示例)——展示 AI 身份码登记格式与溯源字段

compliance_checklistA

生成 AI 治理合规清单(EU AI Act 2024/1689 相关条款 / GB/Z 185 / ISO/IEC 42001 / PIPL·GDPR)——面向自主 agent 注册就绪的自评起点,非法律意见

gov_scanB

通用治理/PII 扫描:手机号、邮箱、本地路径、疑似凭据、密钥特征串 + 版权指纹缺失提示;可用 names 传指名清单(逗号分隔)

lgd_knowledgeB

LGD 全程治理论知识端点:返回三律/三查/规范出处(DOI·仓库·官网),可按主题路由到对应域论文(金融/证据/政务/链上/驾驶/数据/低空/机器人/工业/基因/教育/医械)

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.3/5.0

Scored across 6 tools

Disambiguation4/5

Each tool targets a distinct governance function: evidence generation, risk scoring, identity lookup, compliance checklist generation, PII/secret scanning, and theoretical knowledge retrieval. The main overlap is between audit_evidence_chain and compliance_checklist, as both produce governance/audit documents, but their descriptions make the boundary reasonably clear.

Naming Consistency3/5

All names use snake_case, but the internal pattern is mixed: some are noun_verb (passport_lookup, gov_scan), some noun_noun (compliance_checklist, lgd_knowledge), and one uses a prefixed verb (a3_assess). The abbreviations (a3, gov, lgd) also vary in transparency, though the names remain readable.

Tool Count5/5

Six tools is a well-scoped set for an AI governance advisory server, and each tool covers a different aspect of the domain. There is no obvious redundancy or bloat.

Completeness3/5

The surface covers evidence templates, assessment, identity lookup, compliance checklist generation, scanning, and knowledge retrieval. However, it lacks operational lifecycle tools such as passport registration/update/revocation, actual compliance evaluation against a system, and evidence collection beyond template generation, which are notable gaps for a governance server.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues