npm package lookup by exact name or keyword. Resolution chain: npm CLI (npm view / npm search) → registry API (/-/v1/search) → npms.io web search — stops at the first successful result. Returns name, npmUrl, version, repoUrl, description, and GitHub owner/repo when available. Exact names resolve ...
AI agents call packageSearch to retrieve information from Octocode MCP - AI Context Platform without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
queries | array | Yes | Array of queries for packageSearch. Maximum is 5 queries per call. Multiple queries run in parallel. Use the per-query `page` field to navigate through results. |
Parameters from the server's own tool schema.
This tool retrieves package information from npm and related registries with no side effects. It queries data (npm view, npm search, registry API) and returns structured metadata. There is no creation, modification, deletion, or code execution involved. The tool is purely informational and read-only, making it a Read category risk with low severity.
From the tool's definition Tool performs "npm package lookup by exact name or keyword" and "returns name, npmUrl, version, repoUrl, description, and GitHub owner/repo when available." The resolution chain involves querying npm CLI, registry API, and web search—all read-only operations…
Documented attack patterns abuse exactly the kind of access packageSearch gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Octocode MCP - AI Context Platform, and nothing reaches the server without passing your rules. This is the rule we recommend for packageSearch:
{
"version": "1",
"default": "deny",
"tools": {
"packageSearch": {}
}
}packageSearch is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
npm package lookup by exact name or keyword. Resolution chain: npm CLI (npm view / npm search) → registry API (/-/v1/search) → npms.io web search — stops at the first successful result. Returns name, npmUrl, version, repoUrl, description, and GitHub owner/repo when available. Exact names resolve full metadata; keyword searches return a ranked list. Continue with githubViewRepoStructure or githubSearchCode after resolving the source repo. Use githubSearchRepositories for broad domain searches. It is categorised as a Read tool in the Octocode MCP - AI Context Platform MCP Server, which means it retrieves data without modifying state.
packageSearch accepts 1 parameter: queries. Required: queries. The full parameter table on this page comes from the server's own tool schema.
Register the Octocode MCP - AI Context Platform MCP server in PolicyLayer and add a rule for packageSearch: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Octocode MCP - AI Context Platform. Nothing to install.
packageSearch is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the packageSearch rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for packageSearch. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
packageSearch is provided by the Octocode MCP - AI Context Platform MCP server (octocode-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Octocode MCP - AI Context Platform, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 Octocode MCP - AI Context Platform tools catalogued and risk-classified — across an index of 43,000+ MCP servers.