
Runlog
org.runlogPublished by runlog.orgOfficial publisherv0.1.0Updated Oct 24, 2026
Verified registry of third-party-system knowledge — the external-dependency layer for agent memory.
Overview
Runlog is a hosted MCP endpoint that gives an assistant a verified registry of third-party-system knowledge, acting as an external-dependency layer for agent…
- What you can do
- No tools are listed in the manifest, so capabilities are known only from the description.
- It presents itself as a verified registry of knowledge about third-party systems.
- It is positioned as the external-dependency layer for agent memory, so an assistant can draw on stored knowledge about outside systems rather than relying only on its own context.
- No further operations, read or write, are documented in the supplied material.
- When to use it
- Consider it when an assistant needs dependable, externally maintained knowledge about third-party systems as part of its memory, rather than knowledge it must reconstruct on its own. Because no tools or usage details are published, evaluate it only after confirming what it actually exposes.
- Requirements
- A remote streamable HTTP endpoint at api.runlog.org; nothing runs locally. A bearer token is required in the Authorization header, using an API key issued through the provider's registration page. Network access to the endpoint is needed.
Installation
In SourceWeft
- Open Runlog in the dashboard and add it to a workspace.
- Connect Authorization token credentials. They are stored privately and never shown on public pages.
- 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/org.runlog%2Frunlog/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.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"runlog": {
"type": "http",
"url": "https://api.runlog.org/mcp",
"headers": {
"Authorization": "Bearer <YOUR_TOKEN>"
}
}
}
}README
This repository has no README.
Tools
0Version history
1- v0.1.0LatestSep 16, 2026
Score
35% 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
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- 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.