mcp-registry/network.edge/mcp · v1.0.0
As of 2026-10-17 05:28 UTC, the Edge MCP server is up with a Glimind reliability score of 89/100 (grade B). Over the last 30 days it answered 99.9% of Glimind's liveness checks. It had 108 outages in 90 days, with a median recovery of 3 minutes.
Deploy and manage Edge Network cloud: sites, VMs, storage, DNS, Shield, Assist. Agent self-signup.
Claude Code
claude mcp add --transport http edge-mcp-server https://edge.network/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"edge-mcp-server": {
"type": "http",
"url": "https://edge.network/mcp"
}
}
}
Third-party server, listed as discovered. Review its source before installing.
28 of 28 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.
12 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.
Handshake + tools/list takes ~2,057 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.
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. All of them as JSON: /v1/readiness/mcp-registry%2Fnetwork.edge%2Fmcp/fixes
{
"name": "edge_account_status",
"description": "Check whether the connected account is a self-signed-up guest (explore tier) or fully claimed, and how to unlock it.",
"inputSchema": {
"type": "object",
"properties": {}
},
"annotations": {
"readOnlyHint": true
}
}{
"name": "edge_add_dns_record",
"description": "Add a DNS record to a zone.",
"inputSchema": {
"type": "object",
"required": [
"zone_id",
"type",
"name",
"data"
],
"properties": {
"ttl": {
"type": "number",
"description": "TTL in seconds (default 300)"
},
"data": {
"type": "string",
"description": "Record value, e.g. an IP address or target domain"
},
"name": {
"type": "string",
"description": "Record name, e.g. \"www\" or \"@\" for the root"
},
"type": {
"enum": [
"A",
"AAAA",
"CNAME",
"MX",
"TXT",
"NS"
],
"type": "string",
"description": "Record type"
},
"dry_run": {
"type": "boolean",
"description": "Preview the action without executing it. Returns what would happen, including cost estimates. Always dry-run first for anything that costs money."
},
"zone_id": {
"type": "string",
"description": "Zone id (from edge_list_dns_zones)"
},
"priority": {
"type": "number",
"description": "Priority — required for MX records"
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "edge_create_assist_site",
"description": "Create an Edge Assist site: AI answers for a website, grounded in its own content. Free tier: 1 site, 250 answered questions/month. Returns the sitekey and a one-line embed snippet.",
"inputSchema": {
"type": "object",
"required": [
"name",
"hostname"
],
"properties": {
"name": {
"type": "string",
"description": "Friendly name, e.g. \"Docs site\""
},
"dry_run": {
"type": "boolean",
"description": "Preview the action without executing it. Returns what would happen, including cost estimates. Always dry-run first for anything that costs money."
},
"hostname": {
"type": "string",
"description": "Hostname the widget will run on, e.g. \"docs.example.com\" (origin-enforced)"
},
"index_url": {
"type": "string",
"description": "Public URL of the content index JSON: { \"pages\": [{ \"url\", \"title\", \"text\" }] }. Can be set later."
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}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/network.edge/mcp"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/network.edge/mcp"}) over MCP.
edge_deploy_static_site ~474 tokensedge_deploy_app ~448 tokensedge_update_deployment ~300 tokensedge_update_dns_record ~300 tokensedge_upload_files ~255 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%2Fnetwork.edge%2Fmcp?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fnetwork.edge%2Fmcp?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fnetwork.edge%2Fmcp.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fnetwork.edge%2Fmcp.svg :target: https://glimind.com/server/mcp-registry%2Fnetwork.edge%2Fmcp?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 sha256:8b00d294d265f3f9…, first seen 2026-10-17, included at leaf 7223 of 16,971. Version history · verify what your client received.
Compare: most reliable security servers · most reliable dns servers · most reliable knowledge servers · most reliable storage servers · most reliable devops 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 05:28 UTC, the Edge MCP server is up with a Glimind reliability score of 89/100 (grade B). Over the last 30 days it answered 99.9% of Glimind's liveness checks. It had 108 outages in 90 days, with a median recovery of 3 minutes.
Edge MCP server advertises 28 tools, including edge_account_status, edge_add_dns_record, edge_create_assist_site, edge_create_bucket, edge_create_dns_zone.
Point your MCP client at this streamable-http endpoint: https://edge.network/mcp
Glimind scanned all 28 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.
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.
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.