EdgeDepth Research is answering right now. Last checked 8 min ago. 242 installs a week from npm. Last commit 13 Oct 2026.
Test crypto-perpetual claims using recorded counts, baselines, and replay.
What the code does
We read the source, 5 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
пакет @edgedepth/research-mcp ссылается на jtucker96/edgedepth-research-mcp
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 8 min ago.
claude mcp add research --transport http https://mcp.edgedepth.com/mcphttps://mcp.edgedepth.com/mcp[mcp_servers.research]
url = "https://mcp.edgedepth.com/mcp"{
"mcpServers": {
"research": {
"url": "https://mcp.edgedepth.com/mcp"
}
}
}{
"servers": {
"research": {
"type": "http",
"url": "https://mcp.edgedepth.com/mcp"
}
}
}This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.edgedepth.com/mcp | streamable-http | sign-in | 249 ms | 8 min ago |
Alternatives to EdgeDepth Research
same job, measured the same wayPay-per-call x402 crypto research and Base address/approval risk checks. Testnet by default.
Base crypto safety for agents: honeypot/tax test, address poisoning, rug feed, creator record.
Sell for crypto from your editor: products, payment links, invoices and test payments.
Base-vs-head test result differ: named tests added, removed, and changed, never raw counts.
Search, read, download and report on tested step-by-step recipes (playbooks) for AI agents.
Synthetic US medical-billing documents (PDF and ground truth) for testing extractors and agents
Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.
Evaluate ML features beyond a baseline and test bounded feature repairs. Invite-only beta.
EdgeDepth Research — questions
Answers built from our own checks of this server.