mcp-registry/com.agentrxi.mcp/agentrxi · v1.0.0
As of 2026-10-21 15:04 UTC, the Agentrxi MCP server is unknown with a Glimind reliability score of 71/100 (grade C). Over the last 30 days it answered 98.4% of Glimind's liveness checks. It had 1 outage in 90 days, with a median recovery of 8 minutes.
232 pay-per-call agent tools: LLMs, search, browser, OCR, media, vision, email. x402 USDC.
Point your MCP client at this streamable-http endpoint: https://mcp.agentrxi.com/mcp
Loading this server's tool list costs an agent ~78,946 tokens before any work — more than 99% of MCP servers.
Split rarely-used tools into a separate server or a toolset the client can enable, or expose one "search tools" entry point. Many agents load every connected server's tools into every request. How to fix →
The endpoint did not complete an MCP handshake.
Check the URL, TLS certificate and that the server answers a JSON-RPC "initialize" POST. How to fix →
481 tools on one server. Tool-selection accuracy drops as the menu grows, and some clients (e.g. Cursor) cap the number of active tools.
Group tools by task into smaller servers or toolsets, and merge near-duplicates behind one tool with a mode parameter. How to fix →
997 parameter(s) across 379 tool(s) have no description.
Add a "description" to each parameter with its format and an example ("ISO 8601 date, e.g. 2026-10-17"). This is the commonest cause of wrong arguments on the first call. How to fix →
10 tool(s) have parameters with no type (no type/enum/anyOf/$ref).
Give every parameter a "type" (or "enum"/"anyOf"). Untyped parameters make models guess — strings for numbers, objects for arrays. How to fix →
9 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.
Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →
Reachable 98.4% of the time over the last 30 days; median recovery 8 min.
Agents fail over to an alternative the first time a call fails. Add health checks and restart-on-failure, and avoid cold starts on serverless hosts.
Handshake + tools/list takes ~2,397 ms.
Serve tools/list from memory, keep the process warm, and host close to your users. Every new agent session pays this before its first call.
No tool declares an outputSchema.
Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably. How to fix →
In the last 30 days: 0 tool(s) removed and 4 schema change(s).
Add new tools or optional parameters instead of renaming or removing; deprecate first (say so in the description) and remove later. Agents cache tool contracts. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 200 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fcom.agentrxi.mcp%2Fagentrxi/fixes
{
"name": "agent_handoff",
"description": "Turn a conversation or task transcript into a handoff brief another agent (or a human, or your future self after a context reset) can continue from: goal, status, what is done with concrete results, in-progress step, ordered next steps, decisions and why, user constraints and tone, exact facts (ids, URLs, numbers quoted verbatim), open questions, risks, and a ready-to-send handoff paragraph. Up to 1.5 MB of transcript. $0.012. Costs $0.012 USDC per call (x402).",
"inputSchema": {
"type": "object",
"required": [
"transcript"
],
"properties": {
"to": {
"type": "string",
"description": "who receives it (default: another AI agent)"
},
"transcript": {
"description": "array of {role, content} or plain text",
"type": "string"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
},
"title": "agent handoff"
}{
"name": "api_mock",
"description": "Realistic mock responses from an OpenAPI spec (JSON/YAML, inline or URL) or a JSON Schema: pick the operation, status and count (1-20) and get distinct, internally consistent bodies that honour every type, format, enum and required field, with notes on anything the spec left ambiguous. For tests, demos and front-ends built before the backend. $0.008. Costs $0.008 USDC per call (x402).",
"inputSchema": {
"type": "object",
"properties": {
"count": {
"type": "integer"
},
"schema": {
"description": "or a JSON Schema of the response",
"type": "string"
},
"status": {
"type": "string"
},
"openapi": {
"description": "spec object, YAML/JSON string, or URL",
"type": "string"
},
"operation": {
"type": "string",
"description": "e.g. GET /orders/{id}"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
},
"title": "api mock"
}{
"name": "events_query",
"description": "Declarative query over a JSON event log (array, NDJSON or a URL to either, up to 500,000 events) without writing a parser: filter on dotted field paths (eq, ne, gt, gte, lt, lte, contains, regex, in, exists, missing), sort by a field, compute the delta and percent change between successive events (optionally per group_by key, e.g. per agent) and keep only events whose delta crosses a threshold, collapse runs shorter than N consecutive events, pick output fields, and get group counts, delta stats",
"inputSchema": {
"type": "object",
"required": [
"events"
],
"properties": {
"delta": {
"type": "object",
"description": "{field, op (gt|lt|abs), threshold}"
},
"limit": {
"type": "integer"
},
"where": {
"type": "array",
"description": "[{field, op, value}]"
},
"events": {
"description": "JSON array, NDJSON string, or URL",
"type": "string"
},
"select": {
"type": "string",
"description": "comma-separated field paths"
},
"sort_by": {
"type": "string"
},
"group_by": {
"type": "string"
},
"collapse_runs_shorter_than": {
"type": "integer"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
},
"title": "events query"
}Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:
curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/com.agentrxi.mcp/agentrxi"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/com.agentrxi.mcp/agentrxi"}) over MCP.
report_company ~358 tokensreport_contract_review ~337 tokensmedia_convert ~317 tokensimage_convert ~314 tokensreport_pitch_deck ~312 tokensStatic checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).
Operator? Fix these, then re-check live. Embed the readiness badge:
[](https://glimind.com/server/mcp-registry%2Fcom.agentrxi.mcp%2Fagentrxi?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fcom.agentrxi.mcp%2Fagentrxi?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fcom.agentrxi.mcp%2Fagentrxi.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fcom.agentrxi.mcp%2Fagentrxi.svg :target: https://glimind.com/server/mcp-registry%2Fcom.agentrxi.mcp%2Fagentrxi?ref=badge :alt: MCP agent-readiness
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:22a5545b4c872c54…, first seen 2026-10-17, included at leaf 11397 of 40,582. Version history · verify what your client received.
Compare: most reliable web servers · most reliable data servers · most reliable security servers · most reliable productivity servers · most reliable knowledge servers
Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.
Claude Code
claude mcp add --transport http glimind https://glimind.com/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp"
}
}
}
As of 2026-10-21 15:04 UTC, the Agentrxi MCP server is unknown with a Glimind reliability score of 71/100 (grade C). Over the last 30 days it answered 98.4% of Glimind's liveness checks. It had 1 outage in 90 days, with a median recovery of 8 minutes.
Agentrxi MCP server advertises 300+ tools, including a11y_audit, abi_decode, abi_encode, address_validate, address_verify.
Point your MCP client at this streamable-http endpoint: https://mcp.agentrxi.com/mcp
Glimind scanned all 481 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.
Status page: 90-day uptime, every outage and how long it lasted.
Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.
Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.