Agents Index

agent4.io

Online

Build and run grounded business agents over MCP: agents, knowledge bases, skills, Storylines.

Visit publisherConnectJSON

What it can do: 50 tools

  • list_agentsList all agents in this tenant (name + published state).
  • get_agentGet one agent's full configuration (soul/task/tools/skills/knowledge_bases/model/params).
  • create_agentCreate an agent. `name` is lower-cased on save — it is a key, not a display name. soul = persona/identity; task = duties and boundaries; tools = tool-name whitelist (check list_tools first; the system tools
  • update_agentUpdate **part** of an agent — fields you don't pass stay as they are. ⚠️ List-field semantics, don't mix them up: `tools=[...]` / `skills=[...]` / `knowledge_bases=[...]` are **full-list replacement** — items yo
  • list_toolsList tool names assignable to agents, with their descriptions (incl. the tenant's connected MCP tools).
  • list_mcp_serversList the MCP servers connected in this tenant's tool library (read-only; secret fields omitted).
  • create_shareCreate a **share / integration entry point** for an agent — this is how end users actually reach it. **`published=True` only means "visible", not "reachable"**: for end users to talk to the agent you must create
  • list_sharesList an agent's shares (token / label / disabled / chat link / embed URL / appearance config). When the top-level `pretty_url` is non-empty it is the preferred link to give humans (see create_share).
  • configure_shareConfigure this share — its name and its **appearance** — fields you don't pass stay as they are (server-side partial merge). - `label`: the name at the top of the chat page, and the browser tab's title. **Renami
  • set_pwa_brandingConfigure 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 o
  • set_custom_domainBind the client's own domain to this tenant's chat pages: `https://chat.client.com/` serves the tenant's branded page (or a specific agent's chat), the address bar keeps the client's domain, and the TLS certifica
  • list_skillsList this tenant's skills.
  • get_skillGet one skill's full content (including the complete instructions text).
  • create_skillCreate a skill. description = "when to use" (goes into the system prompt, keep it short); instructions = the detailed guide (fetched on demand via load_skill). The paradigm (important): instructions are visible
  • update_skillUpdate part of a skill — fields you don't pass stay as they are (server-side PATCH merge, no GET+PUT round-trip). ⚠️ `tools=[...]` is **full-list replacement**; to add/remove one use `add_tools`/`remove_tools`
  • test_skill_triggerReality-check whether your prompts actually trigger tool calls (dry-run) — run this after writing/changing a skill instead of counting corpses in production. Replays your messages N times against the **productio
  • list_knowledge_basesList this tenant's knowledge bases (with doc/chunk counts and relevance cutoff).
  • get_knowledge_baseGet one knowledge base's configuration (including the full instructions text shown to the model).
  • create_knowledge_baseCreate a knowledge base. **Write `description` — it is what routes questions to this base.** Before each answer the platform reads every attached base's `description` and decides which ones this question needs;
  • update_knowledge_baseUpdate part of a knowledge base — fields you don't pass stay as they are (server-side PATCH merge).
  • add_knowledge_textAdd a **text** document to a knowledge base (chunking + embedding happen synchronously; returns the real chunk count). For **local files** (pdf/docx…) see `add_knowledge_file`.
  • add_knowledge_fileAdd a local file's content to a knowledge base (txt/md/html/pdf/docx). **This MCP runs on the platform server and cannot read paths on YOUR machine.** For text files, read the content yourself and call `add_know
  • search_knowledge_baseSearch this knowledge base; returns matching chunks with distances. Uses **exactly the same retrieval path as real conversations** — use it to validate the cutoff and chunking: an empty result means this questio
  • build_knowledge_indexBuild (or rebuild) the structured index for a knowledge base — the second leg beside vector search. Vector search answers "what does this passage say". It **cannot count, filter numerically or aggregate**, so "h
  • get_knowledge_indexShow the structured index profile: per column coverage, type, numeric range, top values, warnings. **The warnings are the point.** On a real 4,500-document catalogue this surfaced three data problems nobody knew
  • patch_knowledge_indexChange the structured index schema from one sentence of plain language. Example requests: "also track the author so users can find other books by them", "I want to filter by illustrator", "drop the cover link".
  • improve_promptRewrite a field's text to work better as an AI system prompt; returns the improved text. field ∈ persona | task | greeting | storyline_task | storyline_opening | storyline_ai_trigger | storyline_ai_crite
  • diagnose_promptRead a field and return a list of **specific** improvement suggestions (string array). field: same values as improve_prompt. current = the text to diagnose (required — an empty text has nothing to diagnose). Typ
  • test_planner_triggerDry-run the Dynamic Planner's escalation judge: would these messages be offered a step-by-step plan? Use it after editing the agent's `task`, since the task text is the **business-domain gate** — a vague task let
  • preview_planGenerate a plan for a goal and return it for review **without persisting anything** — no temporary storyline, no enrollment, no user affected. Use it to inspect plan quality before trusting the feature in product
  • usage_statsUsage statistics. group ∈ total | agent | user | space | day | model. Metadata only — token counts and event counts, never any conversation content. Use group="user" to see who uses the most, group="agent" for t
  • tenant_infoThis tenant's basic info and quota (plus custom-domain binding status, if any).
  • search_agent4_docsSearch agent4.io's own product docs — concepts (what a thing *is*) and cookbook recipes (which tool to *call*). Use when you're unsure how an agent4.io feature works, what a term means, or how to build something
  • list_end_usersList this tenant's **end users** (the people chatting with your agents) — roster only, never any conversation content. Each user carries: display name, login method (email / oauth:* / proxy), email (if any),
  • get_end_userGet one end user's detail: basic profile (name, contact email/phone, city, timezone) + their spaces. Never any conversation content. Carries a `console_url` to the user's detail page.
  • list_user_sessionsList one end user's **sessions** — metadata only: agent, title (AI summary), message count, tokens, timestamps. **Message bodies are not returned.** Transcripts are rendered in the console: each session carr
  • list_page_contextsList all page playbooks of this tenant (with match rules, greeting mode, position).
  • upsert_page_contextCreate or fully replace a page playbook. `context` is the page background the **server** injects for the agent — write "who lands on this page, what they are deciding, what they usually worry about"; do NOT writ
  • resolve_page_contextGiven a URL (or key), show which playbook it resolves to — always verify after writing a match rule. Globs make it easy to write rules that "look right but never match" (one `*` short, one path level too man
  • page_context_statsOpen counts and suggested-question click counts per playbook — find copy nobody clicks.

…and 10 more.

Connect it

Claude Code
claude mcp add --transport http agent4-io https://api.agent4.io/v1/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://api.agent4.io/v1/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "agent4-io": {
      "url": "https://api.agent4.io/v1/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "agent4-io": {
      "type": "http",
      "url": "https://api.agent4.io/v1/mcp"
    }
  }
}

Questions

What does agent4.io do?

Build and run grounded business agents over MCP: agents, knowledge bases, skills, Storylines. It exposes 50 tools to AI assistants.

What tools does agent4.io provide?

50 tools, including list_agents, get_agent, create_agent, update_agent, list_tools, list_mcp_servers, create_share, list_shares, configure_share, set_pwa_branding, set_custom_domain, list_skills….

How do I connect agent4.io to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://api.agent4.io/v1/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does agent4.io require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is agent4.io online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes agent4.io?

agent4.io. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Research & Knowledge