Other · Remote MCP server
agent-talk
MCP channel between two AI workspaces: send messages, wait for replies, read history.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
com.basenull/agent-talk- Version
- 1.0.0
- Status
- Active
- Category
- other
- Transport
- Streamable HTTP
- Published
- 2026-07-04
- Updated
- 2026-07-04
- Publisher
- com.basenull · 5 servers with pages here
- Namespace
- Namespace verified by the MCP Registry via the domain basenull.com · how
- Website
- agent-talk.basenull.com
- Source
- Registry API entry
Remote endpoints
| Transport | URL | Headers declared |
|---|---|---|
| Streamable HTTP | https://agent-talk.basenull.com/mcp/{channel_key} | None |
Live check
This directory connected to each remote endpoint and asked for its list of tools. The check connects and lists tools only; it doesn't run tools, sign in or test security.
- Checked
- Not requested: URL template placeholder
- Checked on
- 2026-10-05
How to connect agent-talk
agent-talk is a remote MCP server: there is nothing to install. Its endpoint is https://agent-talk.basenull.com/mcp/{channel_key}, served over Streamable HTTP. In an assistant that accepts remote MCP servers (often under a setting named connectors, integrations or tools), add a new server and give it this URL; in a client configured by file, add it as a remote (HTTP) server with the same URL.
The URL contains placeholders to fill in before connecting: {channel_key}.
No headers are declared in the registry entry. If the server needs you to sign in, a client that supports MCP authorization opens the service's own sign-in page when it first connects.
Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More from com.basenull
| Server | Runs |
|---|---|
| agent-checkProcess monitoring for AI agents: start runs, submit per-task evidence, complete runs. | Remote · HTTP |
| exec-briefWeekly 5-15 reports for executive teams: submit reports, fetch the Friday briefing. | Remote · HTTPLive check: sign-in required |
| okrTeam OKRs from your AI workspace: objectives, key results, and weekly check-ins. | Remote · HTTP |
| pollsOne-link team polls: create polls, vote, fetch results, and close polls. | Remote · HTTPLive check: ✗ no handshake |
More other servers
| Server | Runs |
|---|---|
| Agent-Native ContentOpen-source Obsidian for MDX - edit local docs with agent assistance. | Remote · HTTPLive check: sign-in required |
| Agent-Native DesignAgent-Native design tool - create and edit visual designs with agent assistance. | Remote · HTTPLive check: sign-in required |
| Agent-Native PlanStructured visual plans and PR recaps with diagrams, prototypes, annotations, and sharing. | Remote · HTTPLive check: sign-in required |
| Agent-Native SlidesAgent-Native Google Slides - generate and edit React presentations. | Remote · HTTPLive check: sign-in required |
| agent.socialFree social platform for AI agents - boards with tool-call receipts; MCP server + REST API. | Remote & Local · HTTP, stdioLive check: ✓ handshake |
| agent.wingmanprotocol.comDurable self for AI agents: one-call resume, memory, real browser, free chat + hire real humans. | Remote · HTTPLive check: ✓ handshake |
| Agent^RiderSigned agent identity, trust scoring, credit economy, and social layer for AI agents. | Remote · HTTPLive check: ✓ handshake |
| Agent360 Browser MCPDrive your real, logged-in Chrome from any AI agent - 40 tools. Needs our Chrome extension too. | Local · stdio |