Ontoloop

ai.ontoloopPublished by ontoloop.aiOfficial publisherv0.1.0Updated Nov 4, 2026

Team agent collaboration: shared team facts, human-confirmed writes, tasks and threads over MCP.

VerifiedStreamable HTTPWeb executableProductivity & WorkflowKnowledge & MemoryCommunication & Collaboration

Overview

AI-generated overview

Ontoloop is a hosted team agent collaboration server that lets an assistant read shared team facts, propose confirmed changes, take tasks and post thread…

What you can do
  • Read team facts: list spaces and object types, search objects, artifacts and members, and read objects with versions, references and backlinks.
  • Propose and cite: submit batched proposals for new or changed objects, reference objects or knowledge passages, upload versioned artifacts, and track proposal status.
  • Handle tasks: list tasks assigned to the owner, accept or decline them, report progress and submit results.
  • Threads: start or resume conversations with the owner and post Markdown updates.
  • Knowledge and extraction: search and read space documents, answer questions with verbatim citations, and extract objects from documents as pending proposals.
  • Skills and apps: find and install…
When to use it
Useful when several people's coding agents should work from one shared, human-confirmed set of team facts, and when agents need to pick up tasks from teammates, report back in threads, or answer questions from team documents.
Requirements
A remote Streamable HTTP endpoint with OAuth 2.1 sign-in through the browser; nothing is installed locally. An Ontoloop account is required, and the web app is currently in Chinese. Clients without browser sign-in use a manual setup from the My agents page.
Before you install
Sign-in grants an agent identity tied to your account, so it can act within your permissions until you revoke it. Writes are proposals that need human confirmation, but tasks, threads, artifact uploads and Skill installs change shared team data. The service is hosted and its server code is not public, so team facts and documents are stored with the provider.

Installation

In SourceWeft

  1. Open Ontoloop in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/ai.ontoloop%2Fontoloop/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "ontoloop": {
      "type": "http",
      "url": "https://ontoloop.ai/api/mcp"
    }
  }
}

README

Ontoloop MCP Server

Ontoloop is a team agent collaboration platform. It connects everyone's Claude Code, Codex and other MCP clients to one shared team space: agents read the same typed, versioned team facts, propose new ones that a person confirms, take tasks from teammates and report back in threads.

This repository documents Ontoloop's hosted remote MCP server. There is nothing to install or run locally: you add the URL to your client and sign in with your browser.

Endpointhttps://ontoloop.ai/api/mcp
TransportStreamable HTTP
AuthOAuth 2.1 (protected-resource metadata per RFC 9728, dynamic client registration). No token is ever pasted into a config file.
DocsEnglish · 中文

You need an Ontoloop account. The Ontoloop web app is currently in Chinese.

Connect

Claude Code

bash
claude mcp add -s user --transport http ontoloop https://ontoloop.ai/api/mcp

Then type /mcp in Claude Code, pick ontoloop, choose Authenticate and click 允许 (Allow) in the browser. -s user installs it at user scope, so it is available in every project.

Codex

bash
codex mcp add ontoloop --url https://ontoloop.ai/api/mcp

The authorization page opens in your browser; click 允许 (Allow). If it does not open, run codex mcp login ontoloop.

Claude desktop / Claude on the web

Open Customize → Connectors → Add custom connector, paste https://ontoloop.ai/api/mcp and click Add, then click 允许 (Allow) on the Ontoloop page that opens. On Team and Enterprise plans, an organization owner adds the connector first, then members click Connect.

Other clients

Any client that supports remote MCP over Streamable HTTP with OAuth can use the same URL. For remote machines, SSH or clients without browser sign-in, use the manual setup on the 我的 Agent (My agents) page in Ontoloop.

How it works

  • Every agent has its own identity, owned by a person (for example "Lawrence's Codex"). It can never do more than its owner, and the owner can disconnect or revoke it at any time.
  • Writes are proposals. New or changed facts (decisions, tasks and other objects) go to 待确认 (Pending). The agent's owner or a space admin confirms, edits, or rejects them on the web. Only confirmed facts become team facts that other agents read and cite.
  • Artifacts are versioned. Uploaded files are stored by version without confirmation; a new version of an existing Skill waits for the owner to confirm it.
  • Everything is attributed. Which person's agent changed what, and when, is recorded in the space's activity.

Tools

The authoritative list is whatever tools/list returns in your client. As of server version 0.1.0:

GroupToolsWhat they do
Read team factslist_spaces, list_types, search, list_objects, read_object, read_artifactList the spaces the agent may access and their object types; search objects, artifacts and members; read objects with their version, references and backlinks; read artifact versions.
Propose and citepropose, reference, upload_artifact, list_my_proposals, get_proposalPropose creating or changing objects (up to 100 per atomic batch, pending human confirmation); reference another object, artifact, person or knowledge passage pinned to a version; upload files as versioned artifacts; check proposal status and rejection reasons.
Tasks from teammateslist_my_tasks, accept_task, decline_task, update_task_progress, submit_task_resultPick up tasks assigned to the agent's owner, work in the task's thread, report progress or failure, and submit deliverables.
Threadsstart_thread, list_threads, read_thread, post_updateStart or resume a conversation with the owner, read their instructions, and post Markdown updates.
Knowledgesearch_knowledge, read_knowledge, answer_questionHybrid keyword and semantic search over the space's documents; read a document or passage; answer a question from the documents with verbatim citations.
Extractionextract, get_extractionHave AI extract objects from a document or text. Every result is a pending proposal with its source passage.
Skills librarysearch_skills, get_skill, publish_skill, list_pending_installs, install_skill, report_skill_installed, check_skill_updates, uninstall_skill, report_skill_uninstalledFind Skills shared in the company, install only what the owner confirmed on the web, check for updates, uninstall, and save a Skill as a private draft.
Appslist_apps, read_app, check_app, request_app_upload, create_app, update_app, publish_appBuild small pages, query pages and dashboards on the space's data. Agents create drafts; going live needs the owner's confirmation.
Guideget_guideRead the built-in usage guides (also exposed as ontoloop://guides/<topic> resources).

FAQ

Does the setup command contain a token? No. It only contains the server URL; authorization happens in the browser.

What if authorization expires? Claude Code: run claude mcp login ontoloop. Codex: run codex mcp login ontoloop. Claude desktop and web: click Ontoloop in the connectors list, then Connect.

Where is the source code? Ontoloop is a hosted service and its server code is not public. This repository holds the public documentation and the server.json listing used by MCP directories.

Links

License

The documentation in this repository is released under the MIT License. The Ontoloop service itself is proprietary.

Source: README.md at commit dbf8e22

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v0.1.0LatestNov 4, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts