Provides AI agents with intelligence on the agent payments ecosystem by scanning GitHub, Hacker News, and npm for protocol signals and opportunities.
Also known as goodmeta/intelligence-mcp, @goodmeta/intelligence-mcp
- Stars
- 1
- Tools
- 3
- Downloads, 30 days
- 203
- Latest version
- 0.1.4
- Last commit
- Nov 15, 2026
- License
- Apache-2.0
What is Intelligence MCP?
Intelligence provides AI agents with intelligence on the agent payments ecosystem by scanning GitHub, Hacker News, and npm for protocol signals and opportunities. It exposes 3 tools, such as scan_opportunities, get_protocol_info, compare_protocols.
Summary generated from the project's README
About Intelligence MCP server
Monitoring the agent payments ecosystem for new protocol signals and development opportunities is what intelligence-mcp enables for AI agents. By scanning GitHub, Hacker News, and npm, the server identifies activity related to specific standards like AP2, ACP, x402, MPP, and UCP. It classifies and scores these signals to provide actionable insights directly to your AI client.
Developers can integrate this server into Claude Code by configuring the command and providing a GITHUB_PAT and ANTHROPIC_API_KEY in the environment settings. The server provides three specific tools: scan_opportunities, which carries a cost of $0.01 USDC per use; get_protocol_info for retrieving canonical descriptions of specific protocols; and compare_protocols for generating a side-by-side comparison matrix. This setup allows an agent to understand protocol maturity, layers, and budget limits without manual searching.
What you can do with it
- 1Identify recent payment protocol developmentsAsk the agent to find new repositories or discussions regarding agent payments from the past week.
- 2Compare different payment protocolsRequest a side-by-side analysis of various protocols to see how they handle agent delegation or budget limits.
- 3Research specific protocol detailsRetrieve technical information about a protocol including its creator, maturity level, and its specific layer.
Written from the project's README. Every use case is checked against a quote from it.
How to install Intelligence MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Intelligence MCP in Claude Code
$ claude mcp add --env 'ANTHROPIC_API_KEY=<YOUR_ANTHROPIC_API_KEY>' --env 'GITHUB_PAT=<YOUR_GITHUB_PAT>' intelligence-mcp -- npx -y @goodmeta/intelligence-mcpInstall Intelligence MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"intelligence-mcp": {
"command": "npx",
"args": [
"-y",
"@goodmeta/intelligence-mcp"
],
"env": {
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
"GITHUB_PAT": "<YOUR_GITHUB_PAT>"
}
}
}
}Install Intelligence MCP in VS Code
.vscode/mcp.json
{
"servers": {
"intelligence-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@goodmeta/intelligence-mcp"
],
"env": {
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
"GITHUB_PAT": "<YOUR_GITHUB_PAT>"
}
}
}
}Install Intelligence MCP in VS Code CLI
$ code --add-mcp '{"name":"intelligence-mcp","type":"stdio","command":"npx","args":["-y","@goodmeta/intelligence-mcp"],"env":{"ANTHROPIC_API_KEY":"<YOUR_ANTHROPIC_API_KEY>","GITHUB_PAT":"<YOUR_GITHUB_PAT>"}}'Install Intelligence MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"intelligence-mcp": {
"command": "npx",
"args": [
"-y",
"@goodmeta/intelligence-mcp"
],
"env": {
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
"GITHUB_PAT": "<YOUR_GITHUB_PAT>"
}
}
}
}Install Intelligence MCP in Codex
$ codex mcp add intelligence-mcp --env 'ANTHROPIC_API_KEY=<YOUR_ANTHROPIC_API_KEY>' --env 'GITHUB_PAT=<YOUR_GITHUB_PAT>' -- npx -y @goodmeta/intelligence-mcpInstall Intelligence MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.intelligence-mcp] command = "npx" args = ["-y", "@goodmeta/intelligence-mcp"] [mcp_servers.intelligence-mcp.env] ANTHROPIC_API_KEY = "<YOUR_ANTHROPIC_API_KEY>" GITHUB_PAT = "<YOUR_GITHUB_PAT>"
Install Intelligence MCP in Gemini CLI
$ gemini mcp add -s user -e 'ANTHROPIC_API_KEY=<YOUR_ANTHROPIC_API_KEY>' -e 'GITHUB_PAT=<YOUR_GITHUB_PAT>' intelligence-mcp npx -- -y @goodmeta/intelligence-mcpInstall Intelligence MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"intelligence-mcp": {
"command": "npx",
"args": [
"-y",
"@goodmeta/intelligence-mcp"
],
"env": {
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
"GITHUB_PAT": "<YOUR_GITHUB_PAT>"
}
}
}
}Started by HostedMCP on 16 Nov 2026
We ran this command for @goodmeta/intelligence-mcp 0.1.4 in an isolated container with no network and no keys. It answered and listed 3 tools.
Intelligence MCP tools 3
Read from the server with tools/listscan_opportunitiesRead-onlyScan GitHub, Hacker News, and npm for fresh signals across AP2, ACP, x402, MPP, and UCP. Classifies and scores opportunities.
get_protocol_infoRead-onlyGet details about a specific agent payment protocol (AP2, ACP, x402, MPP, or UCP). Returns creator, layer, maturity, repo URL, and description.
compare_protocolsRead-onlyCompare AP2, ACP, x402, MPP, and UCP across creator, layer, agent delegation, budget limits, cross-merchant coordination, and MCP integration.
| scan_opportunities | Scan GitHub, Hacker News, and npm for fresh signals across AP2, ACP, x402, MPP, and UCP. Classifies and scores opportunities. | Read-only |
| get_protocol_info | Get details about a specific agent payment protocol (AP2, ACP, x402, MPP, or UCP). Returns creator, layer, maturity, repo URL, and description. | Read-only |
| compare_protocols | Compare AP2, ACP, x402, MPP, and UCP across creator, layer, agent delegation, budget limits, cross-merchant coordination, and MCP integration. | Read-only |
Configuration
ANTHROPIC_API_KEYRequiredSecretAnthropic API key for classifying and scoring signals.
GITHUB_PATRequiredSecretGitHub Personal Access Token for scanning repos and issues.
| Name | Description | |
|---|---|---|
| ANTHROPIC_API_KEY | Anthropic API key for classifying and scoring signals. | RequiredSecret |
| GITHUB_PAT | GitHub Personal Access Token for scanning repos and issues. | RequiredSecret |
Automated checks
Ran Nov 12, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSPass
- Destructive tools are labelledPass
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHubIntelligence MCP Server
MCP server that gives AI agents access to agent payments ecosystem intelligence. Scans GitHub, Hacker News, and npm for signals, classifies and scores them, and returns actionable opportunities.
Tools
| Tool | Description | Cost |
|---|---|---|
scan_opportunities |
Scan GitHub, HN, and npm for new repos, packages, and discussions across AP2, ACP, x402, MPP, and UCP. Returns AI-classified and scored opportunities. Use when asking about recent activity or new developments in agent payments. | $0.01 USDC |
get_protocol_info |
Get the canonical description of a specific agent payment protocol including creator, maturity, repo URL, and layer (authorization, commerce, or settlement). Use when asking about a specific protocol. | Free |
compare_protocols |
Side-by-side comparison matrix of all five protocols across creator, layer, agent delegation, budget limits, cross-merchant coordination, and MCP integration. Use when comparing protocols. | Free |
Install
git clone https://github.com/goodmeta/intelligence-mcp.git
cd intelligence-mcp
npm install
cp .env.example .env # add your keys
npm run build
Usage with Claude Code
Add to your Claude Code MCP config:
{
"mcpServers": {
"intelligence": {
"command": "node",
"args": ["/path/to/intelligence-mcp/dist/index.js"],
"env": {
"GITHUB_PAT": "ghp_...",
"ANTHROPIC_API_KEY": "sk-ant-..."
}
}
}
}
Then ask Claude: "Scan for agent payment opportunities from the last 7 days"
Example
> scan_opportunities(days=7, min_score=12)
Found 23 opportunities (99 signals scanned):
[19/20] [contribution] paygraph-ai/paygraph: Policy engine needs cross-gateway budget tracking
Action: File issue about cross-wallet coordination gap
Why: Building agent wallet with spend controls but no cross-gateway budget
https://github.com/paygraph-ai/paygraph
[18/20] [prospect] sentinelx402: Looking for x402 beta testers
Action: Offer to test with agent-verifier integration
...
Data Sources
- GitHub: new repos in tracked orgs + keyword search across all of GitHub
- Hacker News: stories matching agent payment keywords (via Algolia API)
- npm: new packages matching protocol keywords
Built by
Part of the Agent Payments Landscape project.
Intelligence MCP questions
How do I add Intelligence MCP to Claude Code?
Run claude mcp add --env 'ANTHROPIC_API_KEY=<YOUR_ANTHROPIC_API_KEY>' --env 'GITHUB_PAT=<YOUR_GITHUB_PAT>' intelligence-mcp -- npx -y @goodmeta/intelligence-mcp in your terminal. Add --scope user to make it available in every project.
How do I add Intelligence MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Intelligence MCP provide?
It exposes 3 tools, including scan_opportunities, get_protocol_info, compare_protocols.
What can I scan for with this server?
You can scan GitHub, Hacker News, and npm for new repositories, packages, and discussions related to AP2, ACP, x402, MPP, and UCP protocols.
How much does scanning opportunities cost?
Using the scan_opportunities tool costs $0.01 USDC.
Can I compare different payment protocols?
Yes, the server includes a tool to generate a side-by-side comparison matrix of the five protocols across various technical dimensions.