RFP.ai
v1.0.1
ai.rfp/rfp-ai
Draft cited RFP and security questionnaire answers from your knowledge base, with human review
io.github.TheBarmaEffect/glassbox-framework · v1.0.3
Runtime constitutional verification for AI answers — claim reasoning, ECS, red team, audits.
glassbox-framework 是一个MCP Server,收录自 官方 MCP Registry。支持 stdio 传输。本页提供 Cursor、Claude Code 等客户端的安装配置片段。
选择你的平台查看安装方式
{
"mcpServers": {
"glassbox-framework": {
"command": "npx",
"args": [
"-y",
"@glassbox-framework/mcp"
],
"env": {
"ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>"
}
}
}
}ANTHROPIC_API_KEY必填secretYour Anthropic API key (sk-ant-...). Required for the claim extractor, red team, constitution engines, and ECS coherence checks. One v1 tool (generate_trust_card) works without an API key — it's pure assembly + deterministic audit hashing.
GLASSBOX_MODEL可选Override the Claude model used by the verification engines. Defaults to claude-sonnet-4-6.
GLASSBOX_MAX_TOKENS可选Per-engine-call max-tokens cap. Defaults to 2048; raise for verifying long-form content.
GLASSBOX_ECS_MODE可选ECS aggregation mode: arithmetic (weighted mean, default) or geometric (stricter — any zero dimension collapses the total).
v1.0.1
ai.rfp/rfp-ai
Draft cited RFP and security questionnaire answers from your knowledge base, with human review
v1.1.0
io.github.xenarch-ai/xenarch-mcp
Xenarch — x402 MCP server for AI agent payments. Non-custodial, USDC on Base L2.
v1.0.0
com.docimprint/api
AI document intelligence: extract, summarize, claim-check, and notarize with on-chain proofs.
v0.14.0
io.github.blackwell-systems/agent-lsp
Stateful LSP runtime for AI agents — 50+ tools across 30+ languages via MCP.
v0.2.13
io.github.hostinger/hostinger-api-mcp
MCP server for Hostinger API
v0.41.0
io.github.zhitongblog/unterm
The terminal AI agents can drive: spawn panes, run commands, read screens, scrolling screenshots.
{
"id": "io.github.TheBarmaEffect/glassbox-framework",
"type": "mcp-server",
"version": "1.0.3",
"displayName": "glassbox-framework",
"description": "Runtime constitutional verification for AI answers — claim reasoning, ECS, red team, audits.",
"repository": {
"url": "https://github.com/TheBarmaEffect/glassbox",
"source": "github"
},
"distribution": {
"packages": [
{
"registryType": "npm",
"identifier": "@glassbox-framework/mcp",
"version": "1.0.3",
"transport": "stdio",
"environmentVariables": [
{
"name": "ANTHROPIC_API_KEY",
"description": "Your Anthropic API key (sk-ant-...). Required for the claim extractor, red team, constitution engines, and ECS coherence checks. One v1 tool (generate_trust_card) works without an API key — it's pure assembly + deterministic audit hashing.",
"isRequired": true,
"isSecret": true
},
{
"name": "GLASSBOX_MODEL",
"description": "Override the Claude model used by the verification engines. Defaults to claude-sonnet-4-6."
},
{
"name": "GLASSBOX_MAX_TOKENS",
"description": "Per-engine-call max-tokens cap. Defaults to 2048; raise for verifying long-form content."
},
{
"name": "GLASSBOX_ECS_MODE",
"description": "ECS aggregation mode: arithmetic (weighted mean, default) or geometric (stricter — any zero dimension collapses the total)."
}
]
}
],
"remotes": []
},
"dependencies": [],
"installTargets": [
"claude-code",
"claude-desktop",
"cursor",
"vscode"
],
"keywords": [],
"provenance": {
"origin": "official-mcp-registry",
"originalId": "io.github.TheBarmaEffect/glassbox-framework",
"originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.TheBarmaEffect%2Fglassbox-framework/versions/latest",
"isOfficial": true,
"status": "active"
}
}