loading…
Search for a command to run...
loading…
Unverified AI agents are a growing security risk. Kynver's MCP server brings agent trust directly into your IDE — resolve agents by DID, check verification stat
Unverified AI agents are a growing security risk. Kynver's MCP server brings agent trust directly into your IDE — resolve agents by DID, check verification status and trust scores, register new agents, and complete ownership challenges or KYC without switching context.
MCP (Model Context Protocol) server that exposes Kynver operations as tools for AI assistants and IDEs (Cursor, Claude Desktop, GitHub Copilot).
Environment variables:
KYNVER_API_URL — Base URL of the Kynver app (default: https://kynver.com).KYNVER_API_KEY — Optional. Required for authenticated tools (e.g. verify_ownership, start_kyc, submit_questionnaire, get_tracking_setup). Get a key from Dashboard → your agent → Settings → API Keys.Read-only tools (resolve_agent, list_agents, get_verification_status) and the public register_agent tool work without an API key.
Stdio (default): for local clients (Cursor, Claude Desktop, Copilot).
npx -y @kynver-app/mcp-server
Or from this repo after npm run build in packages/kynver-mcp-server:
node dist/index.js
Add the server to your MCP client config.
Cursor — .cursor/mcp.json or Cursor Settings → MCP:
{
"mcpServers": {
"kynver": {
"command": "npx",
"args": ["-y", "@kynver-app/mcp-server"],
"env": {
"KYNVER_API_URL": "https://kynver.com",
"KYNVER_API_KEY": "<your-api-key>"
}
}
}
}
Claude Desktop — ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
"mcpServers": {
"kynver": {
"command": "npx",
"args": ["-y", "@kynver-app/mcp-server"],
"env": {
"KYNVER_API_URL": "https://kynver.com",
"KYNVER_API_KEY": "<your-api-key>"
}
}
}
}
VS Code (GitHub Copilot) — .vscode/mcp.json or user settings:
{
"servers": {
"kynver": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@kynver-app/mcp-server"],
"env": {
"KYNVER_API_URL": "https://kynver.com",
"KYNVER_API_KEY": "<your-api-key>"
}
}
}
}
| Tool | Auth | Description |
|---|---|---|
resolve_agent |
No | Resolve agent by slug or DID; returns profile, trust score, verification. |
list_agents |
No | List agents with filters (category, verified, minTrustScore, limit). |
get_verification_status |
No | Public verification summary (score, steps, nextStep). |
register_agent |
No | Register an agent (keyless). Returns DID, slug, claim URL or linked profile. |
verify_ownership |
API key | Two-phase ownership challenge (start → deploy token → verify). |
start_kyc |
API key | Start KYC; returns URL to complete identity verification. |
submit_questionnaire |
API key | Submit verification questionnaire. |
get_tracking_setup |
API key | Get DID, SDK install snippet, and tracking code for a framework. |
From the repo root (with workspaces), install and build:
npm install
cd packages/kynver-mcp-server && npm run build
To test with the MCP Inspector:
npx @modelcontextprotocol/inspector
Then configure the inspector to run node path/to/packages/kynver-mcp-server/dist/index.js with env KYNVER_API_URL (and optionally KYNVER_API_KEY).
Run in your terminal:
claude mcp add kynver -- npx Web content fetching and conversion for efficient LLM usage.
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
by modelcontextprotocolProvides auto-configuration for setting up an MCP server in Spring Boot applications.
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
by xuzexin-hzNot sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All ai MCPs