Pick the best developer API for a task — returns a ranked shortlist of vendors from the Nextdev Agent Usability Index with: agent-readiness score, use-case fit, and the rationale behind each pick. Takes a free-text
AI agents call recommend_api to retrieve information from Nextdev MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
recommend_api queries and retrieves structured API recommendations data based on input parameters. It has no side effects on any system or data store — it only reads from an index and returns recommendations. This is a classic Read category tool: it searches, filters, and returns information without creating, modifying, or deleting anything.
From the tool's definition Tool description states it 'returns a ranked shortlist' and 'Pick the best developer API' — purely retrieval and ranking of information from the Nextdev Agent Usability Index. No modification, deletion, or execution of external operations.
Documented attack patterns abuse exactly the kind of access recommend_api gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Nextdev MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for recommend_api:
{
"version": "1",
"default": "deny",
"tools": {
"recommend_api": {}
}
}recommend_api 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.
Pick the best developer API for a task — returns a ranked shortlist of vendors from the Nextdev Agent Usability Index with: agent-readiness score, use-case fit, and the rationale behind each pick. Takes a free-text. It is categorised as a Read tool in the Nextdev MCP MCP Server, which means it retrieves data without modifying state.
Register the Nextdev MCP server in PolicyLayer and add a rule for recommend_api: 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 Nextdev MCP. Nothing to install.
recommend_api 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 recommend_api 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 recommend_api. 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.
recommend_api is provided by the Nextdev MCP server (nextdev-labs/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 Nextdev MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
7 Nextdev MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.