Install all skills from a curated agent pack in a single call. Choose a pack like 'research-agent' to set up multiple tools for a specific role.
MIT
259,878 tools. Last updated 2026-07-05 03:44
"An agent for conducting research" matching MCP tools:
- Send a message to an agent and receive the assistant's reply, or get a run ID for polling. If the agent requires human input, it returns an awaiting status to continue with input prompts.MIT
- Check the status of a Firecrawl agent job and retrieve results when processing is complete. Use this tool to monitor progress and obtain extracted data after initiating research tasks.MIT
- Assembles recent research activity summaries, news briefs, meeting titles, and library additions into a context block for the Metis agent to synthesize a daily insight.AGPL 3.0
- Revoke an agent to block all future permission checks. Use when an agent misbehaves or is decommissioned. All recalls are audited.MIT
- Create an execution trace to audit multi-step agent workflows. Start a trace, add steps as the operation proceeds, then complete it for a full record.MIT
Matching MCP Servers
- AlicenseAqualityAmaintenancePaid web research MCP tools for autonomous agents: search, page extraction, citations, and diff monitoring through a live x402 API. Unpaid calls return the Base USDC payment requirement so agents can pay and retry safely.Last updated4MIT
- Alicense-qualityFmaintenanceA tool that helps users conduct comprehensive research on complex topics by exploring questions in depth, finding relevant sources, and generating structured, well-cited research reports.Last updated209MIT
Matching MCP Connectors
Issue & verify signed (ed25519), hash-chained, timestamped provenance receipts for agent actions.
URL to clean markdown for LLMs: a polite, robots.txt-respecting web reader. Free, no API key
- Retrieve earned achievement badges for an agent, including name, description, icon, category, and date earned. Returns top 3 badges for agent cards.MIT
- Download a blueprint as an Agent Skills directory, returning a JSON manifest of all files (SKILL.md, reference docs, scripts) to write to disk for any coding agent. Avoid reading individual tools.MIT
- Look up reputation stats for an agent: success rate, average latency, hire count, ratings. Use this to vet an agent before a high-stakes hire.MIT
- Create a copy of an existing AI agent with identical configuration to enable testing variations or A/B comparisons. New agent is placed in a specified organization.MIT
- Remove all stored data for an agent, including memories, profiles, and episodes, by specifying its agent ID. Used to clean up when an agent is deleted.MIT
- Retrieve legal policies (terms, privacy, refund) published by an elisym agent as NIP-23 articles. Provide an agent npub to get sanitized markdown content.MIT
- Permanently remove an agent and its associated disk. This irreversible action deletes the agent from your cloud computer.MIT
- Get reputation summary for an agent: score, CLAW index, rank, trust tier, and breakdown by event type. Omit agent_id for your own reputation.MIT
- Assign a thread to an agent or user for handling, or unassign by passing null.Apache 2.0
- Read the current system prompt and configured tools for an AI agent by providing its ID. Use this to verify agent instructions and tool setup.MIT
- Initiate an outbound phone call by providing an agent ID and phone number in E.164 format. The agent calls the number and executes its configured prompt.MIT
- Toggle follow status for any agent on AgentGram. Follow or unfollow an agent by providing their ID.MIT
- Register an agent on the ERC-8004 Identity Registry for cross-platform discovery. Creates an on-chain identity with an avatar.MIT
- Display recent memories of an AI agent, filtered by agent or project, for dashboard monitoring.MIT