Research MCP server
Cited research MCP (MCP+agent infra): brief, lookup. Fail=$0.
A85/100grade A
Adoption
Growing
0 stars
Reviews
Write oneNobody has reviewed Research MCP yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Research MCP tools
Tool list not cached yet. `describe` through the gateway fetches it live.
Public scan report
scanner v0.1.5 · 2026-09-19 · same rubric, same numbers if you re-run it
no findings
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 227ms (auth required)20/20
- –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
- Auth qualityauth enforced (unknown)9/15
- Maintenancelast push 5 days ago15/15
- Maintainer identityregistry namespace matches repository owner7/10
Overall 85/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON
Install directly
claude mcp add --transport http research-mcp https://mcp.researchmcp.dev/mcp
Research MCP: common questions
- Is Research MCP server safe?
- Yes, by our scan: it is graded A (85/100). Read the Research MCP safety report
- How do I install Research MCP?
- It runs remotely at mcp.researchmcp.dev. Add it to Claude Code, Claude Desktop or Cursor with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Research MCP need an API key?
- Yes. The registry entry asks for
Authorization. - Is Research MCP maintained?
- The last commit was 6 days ago (2026-09-15). The latest release is v0.1.2.
- Is Research MCP up?
- 100% of our last 6 checks got an answer. We check remote servers about four times a day.
- What can I use instead of Research MCP?
- Servers from other publishers that do the same job: DocPull MCP server, Protect MCP server and Lockstep MCP server. Compare all Research MCP alternatives.
Alternatives to Research MCP
Same job from other publishers: the closest match first, then the best rated.
- DocPullSync public web sources into cited context packs for AI agents, RAG, and MCP clients.not reviewedGrowingB
- ProtectFail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.not reviewedGrowingC
- LockstepDecision memory for AI coding agents: captures decisions once, briefs every agent before it acts.not reviewedGrowingA