List your agent

agent4.io

MCP server● Hosted · onlinev1.4.0

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

What you can do with it

Share of each task's required capabilities it covers

Prefer a ready-made agent?

An MCP server is a connector for your own assistant. These finished products do the job for you: build a help center.
All AI agents to build a help center, ranked →

Similar tools

Listed for the same task: build a help center

Reviews

No review yet. Used agent4.io? Be the first to help others choose.

What it does

agent4.io is an MCP server, a connector that lets an AI assistant use it as a tool. It is hosted: an assistant connects to it over the internet, nothing to install.

From the publisher's description, Electra Index matched it to one capability: knowledge base qa. That makes it a candidate for tasks such as build a help center or answer customer questions.

Facts come from the Official MCP Registry, as declared by the publisher. Capabilities are matched automatically (low confidence). None of this is a test of the tool.

At a glance

Hosted (remote)YES
Local installNO
Version1.4.0
PriceNot in the registry
First seen26 Sept 2026
Last checked23h ago

How to connect

As declared in the Official MCP Registry · hosted endpoint tested by Electra Index 2d ago (live check)

Hosted endpoint

  • https://api.agent4.io/v1/mcp streamable-http

Required: X-API-Key (get it from the publisher)

MCP settings (Claude Desktop, Cursor and other MCP clients)

{
  "mcpServers": {
    "agent4-io": {
      "url": "https://api.agent4.io/v1/mcp",
      "headers": {
        "X-API-Key": "<your X-API-Key>"
      }
    }
  }
}

Replace the values in <angle brackets>.

Live check

Electra Index connected to the hosted endpoint 2d ago

ONLINE agent4.io answered an MCP connection on 14 Nov 2026 and introduced itself as agent4-io (MCP protocol 2025-06-18).

50 tools offered to AI assistants

  • list_agents · List all agents in this tenant (name + published state).
  • get_agent · Get one agent's full configuration (soul/task/tools/skills/knowledge_bases/model/params).
  • create_agent · Create 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 time/geo/weather **and `compute_c
  • update_agent · Update **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 you didn't read first get pushe
  • list_tools · List tool names assignable to agents, with their descriptions (incl. the tenant's connected MCP tools).
  • list_mcp_servers · List the MCP servers connected in this tenant's tool library (read-only; secret fields omitted).
  • create_share · Create 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 a share. The response carrie
  • list_shares · List 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_share · Configure 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. **Renaming a share is this call**; yo
  • 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). - `agent`: the agen
  • set_custom_domain · Bind 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 certificate is issued automatically.
  • list_skills · List this tenant's skills.
Show 38 more
  • get_skill · Get one skill's full content (including the complete instructions text).
  • create_skill · Create 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 only AFTER the model calls lo
  • 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). ⚠️ `tools=[...]` is **full-list replacement**; to add/remove one use `add_tools`/`remove_tools` (incremental, idempotent). Too
  • 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. Replays your messages N times against the **production** system-prompt assembly, t
  • list_knowledge_bases · List this tenant's knowledge bases (with doc/chunk counts and relevance cutoff).
  • get_knowledge_base · Get one knowledge base's configuration (including the full instructions text shown to the model).
  • create_knowledge_base · Create 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; a base whose description is v
  • update_knowledge_base · Update part of a knowledge base — fields you don't pass stay as they are (server-side PATCH merge).
  • add_knowledge_text · Add 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_file · Add 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_knowledge_text`; for binaries (pd
  • search_knowledge_base · Search 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 question will be judged "not covered
  • build_knowledge_index · Build (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 "how many documents", "which on
  • get_knowledge_index · Show 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 about: 1,058 documents with
  • patch_knowledge_index · Change 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". The model may only emit add/m
  • improve_prompt · Rewrite 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_criteria | skill_description | skill_instr
  • diagnose_prompt · Read 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). Typical flow: diagnose_prompt fi
  • test_planner_trigger · Dry-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 lets out-of-domain requests thr
  • preview_plan · Generate 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 production, or to see how the agent
  • usage_stats · Usage 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 the busiest agent.
  • tenant_info · This tenant's basic info and quota (plus custom-domain binding status, if any).
  • search_agent4_docs · Search 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 on the platform. Returns top
  • list_end_users · List 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), space/session/document counts, l
  • get_end_user · Get 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_sessions · List 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 carries a `console_url` that **deep-l
  • list_page_contexts · List all page playbooks of this tenant (with match rules, greeting mode, position).
  • upsert_page_context · Create 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 write facts like prices or quotas
  • resolve_page_context · Given 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 many) — and in production the only s
  • page_context_stats · Open counts and suggested-question click counts per playbook — find copy nobody clicks.
  • list_storylines · List this tenant's storylines (optionally filtered by agent). Includes state, version, default flag.
  • get_storyline · Get one storyline's full definition (whole graph + profile_schema + top-level fields).
  • create_storyline · Create a storyline draft. After creating, self-check with validate_storyline, then publish_storyline. user_visibility — what the end user sees of their own run: "invisible" (default, no UI), "named" (a banner with the storyline name only),
  • 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). concurrency: "user" = progress belongs to the person (shared across sessions); "session" = progress belongs to t
  • validate_storyline · Validate the storyline graph (entry / dead ends / unreachable / dangling / cross-line targets / rule dimensions). Returns {ok, errors}. Must pass before publishing.
  • publish_storyline · Publish a storyline: validates first (blocking errors → 422), then freezes an immutable version and marks it published.
  • 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).
  • clone_storyline · Clone a storyline into a new draft (new key, unpublished, doesn't claim default, no chain pointer) for tweaking.
  • export_storyline · Export a portable storyline JSON (schema_version + definition; no tenant/version/id) for backup, migration or re-import.
  • import_storyline · Import an exported storyline JSON as a draft. **Artifacts like "generate a storyline from a novel / source material" land here.** payload = the structure returned by export_storyline (schema_version + graph + profile_schema + top-level fiel

What "online" means: the server answered an MCP connection at the time of the check. It is not a guarantee of security, quality or continuous uptime. How we test: we open an MCP session and ask for the tool list, as an AI assistant would. We never run a tool and never send a key. Checked every few days. Method

Is this your server? Monitoring Pro: a check every 30 minutes and an email within the hour when it stops answering. Launch offer: $39.99 once, for life.

Facts & evidence

Each fact shows where it was seen and when.
FactValueEvidenceSourceLast confirmed
Hosted endpointhttps://api.agent4.io/v1/mcpDECLAREDSRC-001 Official MCP Registry23h ago
Local install (package)noDECLAREDSRC-001 Official MCP Registry23h ago
Remote access (hosted)yesDECLAREDSRC-001 Official MCP Registry23h ago
Websitehttps://agent4.ioDECLAREDSRC-001 Official MCP Registry23h ago
Registry statusactiveDECLAREDSRC-001 Official MCP Registry23h ago
Version1.4.0DECLAREDSRC-001 Official MCP Registry23h ago
MCP serveryesDECLAREDSRC-001 Official MCP Registry23h ago

Change history

Baseline
No change detected yet. History builds up as the robots revisit this server.

Is this page accurate?

Flag it and our robot re-checks the official source. Reports never change a score.

Do you run agent4.io? Know when it stops answering

For publishers · optional

Its hosted endpoint can be monitored. Monitoring Pro connects every 30 minutes like an AI assistant, emails you within the hour when it stops answering, keeps a 90-day availability history and adds your answer rate to your badge.

Monitor agent4.ioLaunch offer $39.99 once, for life instead of $9.99/month · All plans

Monitoring never changes a score or a rank.

Are you the publisher of agent4.io?

Free · show your listing

An independent listing builds trust with your buyers. Announce it, and add the badge to your website or README.

Announce it on LinkedIn
Listed on Electra IndexListed on Electra Index
<a href="https://electraindex.com/mcp/agent4-io?utm_source=badge&utm_medium=share&utm_campaign=listing"><img src="https://electraindex.com/api/badge/agent4-io/card" width="260" height="72" alt="Listed on Electra Index"></a>

Questions about agent4.io

How do I connect agent4.io?

Use the hosted endpoint https://api.agent4.io/v1/mcp in your assistant's MCP settings. The exact settings are in "How to connect" above, as declared in the Official MCP Registry.

Does agent4.io need an API key or token?

Yes. The registry entry lists a required value: X-API-Key. Get it from the publisher.

What tools does agent4.io offer?

When Electra Index connected on 14 Nov 2026, it listed 50 tools: list_agents, get_agent, create_agent, update_agent, list_tools, list_mcp_servers, create_share, list_shares and more. The full list is in "Live check" above.

Is agent4.io online?

Yes. Its hosted endpoint answered an MCP connection from Electra Index 2d ago.

What can I use agent4.io for?

Based on its description, it is most relevant to: build a help center, answer customer questions, answer questions from internal documents, answer support phone calls.