mcp-registry/io.agent4/agent4-io
Also listed as mcp-registry/io.agent4/agent4-tenant
As of 2026-10-20 09:40 UTC, the Agent4 Io MCP server is up with a Glimind reliability score of 97/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 28 outages in 90 days, with a median recovery of 2 minutes.
Build and run grounded business agents over MCP: agents, knowledge bases, skills, Storylines.
Claude Code
claude mcp add --transport http agent4-io-mcp-server https://api.agent4.io/v1/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"agent4-io-mcp-server": {
"type": "http",
"url": "https://api.agent4.io/v1/mcp"
}
}
}
Third-party server, listed as discovered. Review its source before installing.
50 of 50 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 →
50 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 →
174 parameter(s) across 42 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 →
14 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 →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 42 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fio.agent4%2Fagent4-io/fixes
{
"name": "add_knowledge_file",
"description": "Add a local file's content to a knowledge base (txt/md/html/pdf/docx).\n\n **This MCP runs on the platform server and cannot read paths on YOUR machine.** For text\n files, read the content yourself and call `add_knowledge_text`; for binaries (pdf/docx),\n upload via the console, or curl `/knowledge-bases/{name}/documents/upload`.\n\n **To ingest a whole folder, zip it and send that one endpoint** — subdirectories are walked,\n md/txt/pdf/html/docx are ingested one by one, and document n",
"inputSchema": {
"type": "object",
"title": "add_knowledge_fileArguments",
"required": [
"kb_name",
"path"
],
"properties": {
"path": {
"type": "string",
"title": "Path"
},
"title": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Title",
"default": null
},
"kb_name": {
"type": "string",
"title": "Kb Name"
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "add_knowledge_text",
"description": "Add a **text** document to a knowledge base (chunking + embedding happen synchronously;\n returns the real chunk count).\n\n For **local files** (pdf/docx…) see `add_knowledge_file`.\n ",
"inputSchema": {
"type": "object",
"title": "add_knowledge_textArguments",
"required": [
"kb_name",
"title",
"content"
],
"properties": {
"title": {
"type": "string",
"title": "Title"
},
"content": {
"type": "string",
"title": "Content"
},
"kb_name": {
"type": "string",
"title": "Kb Name"
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "create_agent",
"description": "Create an agent.\n\n `name` is lower-cased on save — it is a key, not a display name.\n\n soul = persona/identity; task = duties and boundaries; tools = tool-name whitelist (check\n list_tools first; the system tools time/geo/weather **and `compute_chart`** are\n **auto-enabled by default**, no need to list them — but note that passing `tools` at all\n replaces that default list, so include them yourself if you pass any);\n knowledge_bases = attached knowledge base names (once attached",
"inputSchema": {
"type": "object",
"title": "create_agentArguments",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"title": "Name"
},
"soul": {
"type": "string",
"title": "Soul",
"default": ""
},
"task": {
"type": "string",
"title": "Task",
"default": ""
},
"alias": {
"type": "string",
"title": "Alias",
"default": ""
},
"model": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Model",
"default": null
},
"tools": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Tools",
"default": null
},
"skills": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Skills",
"default": null
},
"ask_forms": {
"type": "boolean",
"title": "Ask Forms",
"default": true
},
"published": {
"type": "boolean",
"title": "Published",
"default": false
},
"knowledge_bases": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Knowledge Bases",
"default": null
}
}
},
"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/io.agent4/agent4-io"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/io.agent4/agent4-io"}) over MCP.
update_agent ~792 tokensupdate_storyline ~716 tokenscreate_storyline ~575 tokensconfigure_share ~418 tokenscreate_agent ~394 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%2Fio.agent4%2Fagent4-io?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fio.agent4%2Fagent4-io?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.agent4%2Fagent4-io.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.agent4%2Fagent4-io.svg :target: https://glimind.com/server/mcp-registry%2Fio.agent4%2Fagent4-io?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 sha256:06ac957783fe71d8…, first seen 2026-10-17, included at leaf 10119 of 32,142. Version history · verify what your client received.
Compare: most reliable files servers · most reliable knowledge servers · most reliable other servers · most reliable devops servers · most reliable ml 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 2026-10-20 09:40 UTC, the Agent4 Io MCP server is up with a Glimind reliability score of 97/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 28 outages in 90 days, with a median recovery of 2 minutes.
Agent4 Io MCP server advertises 50 tools, including add_knowledge_file, add_knowledge_text, build_knowledge_index, clone_storyline, configure_share.
Point your MCP client at this streamable-http endpoint: https://api.agent4.io/v1/mcp
Glimind scanned all 50 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.