AI & Machine Learning

agent4.io

Manage the lifecycle of AI agents, including creation, configuration, and updates.

1 endpoint50 known toolsFirst detected July 29, 2026Last detected August 29, 2026

ENDPOINT 1

https://api.agent4.io/v1/mcp

No auth detected

MCP server metadata

Name: agent4-io

Capabilities

experimentalpromptsresourcestools

Known tools 50

list_agents

List all agents in this tenant (name + published state).

Inferred read-only

get_agent

Get one agent's full configuration (soul/task/tools/skills/knowledge_bases/model/params).

Inferred read-only

create_agent

Create an agent.

Potential side effects

update_agent

Update **part** of an agent — fields you don't pass stay as they are.

Potential side effects

list_tools

List tool names assignable to agents, with their descriptions (incl.

Inferred read-only

list_mcp_servers

List the MCP servers connected in this tenant's tool library (read-only; secret fields omitted).

Inferred read-only

create_share

Create a **share / integration entry point** for an agent — this is how end users actually reach it.

Potential side effects

list_shares

List an agent's shares (token / label / disabled / chat link / embed URL / appearance config).

Inferred read-only

configure_share

Configure this share — its name and its **appearance** — fields you don't pass stay as they are (server-side partial merge).

Inferred read-only

set_pwa_branding

Configure a specific **agent's** PWA branding and install experience (applies to that agent's `/s/` standalone chat pages — what gets installed to the home screen is one agent's entry page, so each agent is its own app).

Inferred read-only

set_custom_domain

Bind the client's own domain to this tenant's chat pages: `https://chat.

Inferred read-only

list_skills

List this tenant's skills.

Inferred read-only

get_skill

Get one skill's full content (including the complete instructions text).

Inferred read-only

create_skill

Create a skill.

Potential side effects

update_skill

Update part of a skill — fields you don't pass stay as they are (server-side PATCH merge, no GET+PUT round-trip).

Potential side effects

test_skill_trigger

Reality-check whether your prompts actually trigger tool calls (dry-run) — run this after writing/changing a skill instead of counting corpses in production.

Inferred read-only

list_knowledge_bases

List this tenant's knowledge bases (with doc/chunk counts and relevance cutoff).

Inferred read-only

get_knowledge_base

Get one knowledge base's configuration (including the full instructions text shown to the model).

Inferred read-only

create_knowledge_base

Create a knowledge base.

Potential side effects

update_knowledge_base

Update part of a knowledge base — fields you don't pass stay as they are (server-side PATCH merge).

Potential side effects

add_knowledge_text

Add a **text** document to a knowledge base (chunking + embedding happen synchronously; returns the real chunk count).

Inferred read-only

add_knowledge_file

Add a local file's content to a knowledge base (txt/md/html/pdf/docx).

Inferred read-only

search_knowledge_base

Search this knowledge base; returns matching chunks with distances.

Inferred read-only

build_knowledge_index

Build (or rebuild) the structured index for a knowledge base — the second leg beside vector search.

Inferred read-only

get_knowledge_index

Show the structured index profile: per column coverage, type, numeric range, top values, warnings.

Inferred read-only

patch_knowledge_index

Change the structured index schema from one sentence of plain language.

Inferred read-only

improve_prompt

Rewrite a field's text to work better as an AI system prompt; returns the improved text.

Inferred read-only

diagnose_prompt

Read a field and return a list of **specific** improvement suggestions (string array).

Inferred read-only

test_planner_trigger

Dry-run the Dynamic Planner's escalation judge: would these messages be offered a step-by-step plan?

Inferred read-only

preview_plan

Generate a plan for a goal and return it for review **without persisting anything** — no temporary storyline, no enrollment, no user affected.

Inferred read-only

usage_stats

Usage statistics.

Inferred read-only

tenant_info

This tenant's basic info and quota (plus custom-domain binding status, if any).

Inferred read-only

search_agent4_docs

Search agent4.

Inferred read-only

list_end_users

List this tenant's **end users** (the people chatting with your agents) — roster only, never any conversation content.

Inferred read-only

get_end_user

Get one end user's detail: basic profile (name, contact email/phone, city, timezone) + their spaces.

Potential side effects

list_user_sessions

List one end user's **sessions** — metadata only: agent, title (AI summary), message count, tokens, timestamps.

Potential side effects

list_page_contexts

List all page playbooks of this tenant (with match rules, greeting mode, position).

Inferred read-only

upsert_page_context

Create or fully replace a page playbook.

Potential side effects

resolve_page_context

Given a URL (or key), show which playbook it resolves to — always verify after writing a match rule.

Inferred read-only

page_context_stats

Open counts and suggested-question click counts per playbook — find copy nobody clicks.

Inferred read-only

list_storylines

List this tenant's storylines (optionally filtered by agent).

Inferred read-only

get_storyline

Get one storyline's full definition (whole graph + profile_schema + top-level fields).

Inferred read-only

create_storyline

Create a storyline draft.

Potential side effects

update_storyline

Update **part** of a storyline draft — fields you don't pass stay as they are (GET-then-merge on top of a full PUT underneath).

Potential side effects

validate_storyline

Validate the storyline graph (entry / dead ends / unreachable / dangling / cross-line targets / rule dimensions).

Inferred read-only

publish_storyline

Publish a storyline: validates first (blocking errors → 422), then freezes an immutable version and marks it published.

Potential side effects

unpublish_storyline

Unpublish (archive): no more auto-enrolment; in-flight users silently degrade to the plain agent on their next turn (progress kept — re-publishing resumes it).

Inferred read-only

clone_storyline

Clone a storyline into a new draft (new key, unpublished, doesn't claim default, no chain pointer) for tweaking.

Inferred read-only

export_storyline

Export a portable storyline JSON (schema_version + definition; no tenant/version/id) for backup, migration or re-import.

Inferred read-only

import_storyline

Import an exported storyline JSON as a draft.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agent4-io]
url = "https://api.agent4.io/v1/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agent4-io": {
      "type": "http",
      "url": "https://api.agent4.io/v1/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agent4-io
Remote MCP URL: https://api.agent4.io/v1/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agent4-io": {
      "url": "https://api.agent4.io/v1/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agent4-io": {
      "type": "http",
      "url": "https://api.agent4.io/v1/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agent4-io",
  "transport": "streamable-http",
  "url": "https://api.agent4.io/v1/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for agent4.io was fetched 2026-09-04T15:04:22.035Z.

Trust status Trusted

agent4.io is assessed as Trusted: Domain has an established technology history spanning over a year.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.