# search_github

GitHub repository discovery — top repos by stars (name, language, description, forks, topics) for any keyword. For dev a Cost: $0.005–$0.05 USDC on Base per call.

Agent View of the PolicyLayer registry record for `search_github`. HTML page: https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/search-github

## Facts

- Tool: `search_github`
- Server: Omnicall — Agent Tools Gateway (`https://omnicall.gocreativeai.com/mcp`) — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools.md
- Homepage: https://github.com/https://omnicall.gocreativeai.com/mcp
- Risk category: Read (Low risk)
- Registry record: grade C, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 1 (1 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `arg` | string | yes |  |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "search_github",
    "arguments": {
      "arg": "<arg>"
    }
  }
}
```

## Why search_github is rated Low

This tool queries publicly available GitHub metadata and returns search results. It has no side effects, cannot modify or delete data, and poses minimal risk even if misused by an AI agent. The cost is negligible ($0.005–$0.05 USDC). Classification as Read is appropriate.

From the tool's own definition: "Tool performs 'GitHub repository discovery' returning 'top repos by stars (name, language, description, forks, topics)' — purely informational retrieval with no data modification, deletion, or execution capabilities."

## Use case

AI agents call search_github to retrieve information from Omnicall — Agent Tools Gateway without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Omnicall — Agent Tools Gateway:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "search_github": {}
  }
}
```

## Other tools on Omnicall — Agent Tools Gateway (78)

- `ai_ask` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/ai-ask.md
- `ai_eco` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/ai-eco.md
- `ai_extract` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/ai-extract.md
- `ai_image` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/ai-image.md
- `ai_music` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/ai-music.md
- `ai_pro` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/ai-pro.md
- `ai_research` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/ai-research.md
- `ai_sandbox` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/ai-sandbox.md
- `ai_speech` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/ai-speech.md
- `ai_summarize` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/ai-summarize.md
- `ai_transcribe` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/ai-transcribe.md
- `ai_ultra` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/ai-ultra.md
- `ai_video` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/ai-video.md
- `crypto_chains` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/crypto-chains.md
- `crypto_defi_tvl` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/crypto-defi-tvl.md
- `crypto_dex` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/crypto-dex.md
- `crypto_exchanges` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/crypto-exchanges.md
- `crypto_fear_greed` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/crypto-fear-greed.md
- `crypto_gas` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/crypto-gas.md
- `crypto_global` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/crypto-global.md
- `crypto_history` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/crypto-history.md
- `crypto_market` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/crypto-market.md
- `crypto_price` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/crypto-price.md
- `crypto_protocols` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/crypto-protocols.md
- `crypto_stablecoins` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/crypto-stablecoins.md
- `crypto_treasury` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/crypto-treasury.md
- `crypto_trending` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/crypto-trending.md
- `crypto_yields` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/crypto-yields.md
- `defi` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/defi.md
- `dex` — Read — https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools/dex.md
- …and 48 more: https://policylayer.com/tools/com-gocreativeai-omnicall-agent-tools.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=com-gocreativeai-omnicall-agent-tools · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/com-gocreativeai-omnicall-agent-tools