DeepResearch
DeepResearch MCP Server provides AI assistants with a structured approach to conducting multi-step web research. It leverages Firecrawl for web searches and OpenAI's GPT-4 for analyzing findings and generating comprehensive reports. The server implements a stateful research process that iteratively explores topics at configurable depths, with each step analyzing previous findings to determine the next search query. Built with TypeScript and the Model Context Protocol, it features robust error handling, token optimization for large research sessions, and both step-by-step and one-shot research workflows. This implementation is particularly valuable for users who need thorough, citation-rich research reports on complex topics without manually managing the search and synthesis process.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- browser-automation
- Source
- PulseMCP
- Repository
- github.com/ameeralns/deepresearchmcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve DeepResearch from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.