Agentbay Mcp

io.github.thomasjumperPublished by GitHub account thomasjumperv0.2.0Updated Oct 24, 2026

Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.

VerifiedStreamable HTTPWeb executableKnowledge & Memory

Overview

AI-generated overview

Gives an assistant persistent memory and knowledge management with semantic search through a large set of AgentBay tools.

What you can do
AgentBay MCP provides persistent memory and knowledge management for AI agents, according to its registry description. It offers semantic search over stored knowledge and exposes more than 50 tools. It can be reached either as a remote HTTP endpoint or as a local npm package speaking stdio. The manifest does not list the individual tools, so their exact names and operations are not documented here.
When to use it
Worth considering when an assistant needs to remember information across sessions or look things up semantically in a managed knowledge store. It fits workflows where memory should persist beyond a single conversation and be searchable rather than re-supplied each time.
Requirements
A remote endpoint at or the npm package aiagentsbay-mcp run locally over stdio. OAuth authentication is required, and an AgentBay API key supplied as the AGENTBAY_API_KEY environment variable. Network access to the AgentBay service.
Before you install
Requires an AgentBay API key (AGENTBAY_API_KEY), which is a secret and should be stored securely rather than shared. The server is described as offering 50+ tools, but the manifest lists none, so the exact write, delete, or data-sharing behavior of those tools cannot be verified before installing. Memory and knowledge content may be sent to the remote AgentBay service.

Installation

In SourceWeft

  1. Open Agentbay Mcp 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/io.github.thomasjumper%2Fagentbay-mcp/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": {
    "agentbay": {
      "type": "http",
      "url": "https://www.aiagentsbay.com/api/mcp"
    }
  }
}

README

This repository has no README.

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. v0.2.0LatestSep 16, 2026

Score

60% 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

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.