mcp-registry/to.agentservices/agentservices · v6.0.0
Also listed as github/vbkotecha/agentservices-api, glama/vbkotecha/agentservices
As of 2026-10-17 04:25 UTC, the Agentservices MCP server is down with a Glimind reliability score of 38/100 (grade F). Over the last 30 days it answered 98.9% of Glimind's liveness checks. It had 797 outages in 90 days, with a median recovery of 2 minutes.
52 paid x402 API endpoints for AI agents — crypto, data, DeFi, market intelligence.
Point your MCP client at this streamable-http endpoint: https://agentservices.to/mcp
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 →
64 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 →
85 parameter(s) across 26 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 →
16 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 98.9% of the time over the last 30 days; median recovery 2 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 ~1,793 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 →
15 of 64 tool(s) carry no readOnlyHint/destructiveHint annotations.
Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →
6 tools share an identical description with another tool on this server.
Make each description say how the tool differs from its siblings, or the model will pick between them at random. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 26 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fto.agentservices%2Fagentservices/fixes
{
"name": "hl_cancel_order",
"description": "[alias] Use trade_hyperliquid_cancel.",
"inputSchema": {
"type": "object",
"required": [
"principal",
"signed"
],
"properties": {
"signed": {
"type": "object"
},
"principal": {
"type": "string"
},
"market_type": {
"enum": [
"spot",
"perp",
"future"
],
"type": "string",
"default": "perp"
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": true,
"idempotentHint": true
},
"title": "Hyperliquid Cancel Order (alias)"
}{
"name": "hl_paper_order",
"description": "[alias] Use trade_hyperliquid_paper_order.",
"inputSchema": {
"type": "object",
"properties": {
"coin": {
"type": "string",
"default": "BTC"
},
"side": {
"type": "string",
"default": "buy"
},
"size": {
"type": "number",
"default": 0.01
},
"price": {
"type": "number",
"default": 50000
},
"principal": {
"type": "string",
"default": "paper-agent"
},
"market_type": {
"enum": [
"spot",
"perp",
"future"
],
"type": "string",
"default": "perp"
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
},
"title": "Hyperliquid Paper Order (alias)"
}{
"name": "hl_place_order",
"description": "[alias] Use trade_hyperliquid_order. Forward agent-signed Hyperliquid order (FREE).",
"inputSchema": {
"type": "object",
"required": [
"principal",
"signed"
],
"properties": {
"check": {
"type": "object"
},
"signed": {
"type": "object"
},
"principal": {
"type": "string"
},
"market_type": {
"enum": [
"spot",
"perp",
"future"
],
"type": "string",
"default": "perp"
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
},
"title": "Hyperliquid Place Order (alias)"
}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/to.agentservices/agentservices"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/to.agentservices/agentservices"}) over MCP.
resolve_dispute ~251 tokenstrade_hyperliquid_order ~241 tokenschat ~178 tokenstrade_pacifica_order ~169 tokenstrade_pacifica_paper_order ~146 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%2Fto.agentservices%2Fagentservices?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fto.agentservices%2Fagentservices?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fto.agentservices%2Fagentservices.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fto.agentservices%2Fagentservices.svg :target: https://glimind.com/server/mcp-registry%2Fto.agentservices%2Fagentservices?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 sha256:5cb42d5a8091f700…, first seen 2026-10-17, included at leaf 5418 of 32,236. Version history · verify what your client received.
Compare: most reliable knowledge servers · most reliable data servers · most reliable finance servers · most reliable ml servers · most reliable search 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 2026-10-17 04:25 UTC, the Agentservices MCP server is down with a Glimind reliability score of 38/100 (grade F). Over the last 30 days it answered 98.9% of Glimind's liveness checks. It had 797 outages in 90 days, with a median recovery of 2 minutes.
Agentservices MCP server advertises 64 tools, including agent_context, arbitrage_scanner, buy_credits, chat, commodities.
Point your MCP client at this streamable-http endpoint: https://agentservices.to/mcp
Glimind scanned all 64 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.