Sitalk MCP server
online · 100% uptimeio.github.David-glitc/sitalk·v0.2.0Find people with real experience. Bring their approved workflows and decisions into your agent.
0 stars
Reviews
Write oneNobody has reviewed Sitalk yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Sitalk tools
Tool list not cached yet. `describe` through the gateway fetches it live.
Public scan report
scanner v0.1.10 · 2026-10-14 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 389ms (auth required)20/20
- –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
- Auth qualityOAuth resource metadata advertised on 40115/15
- Maintenancelast push 9 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Sitalk compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 97/100
- higher than 98% of 4,460 AI and agents servers
- Uptime
- 100%
- of our recent checks; the typical remote AI and agents server answers 100%
- Response time
- 791 ms
- faster than 14% of 2,331 AI and agents servers
Install Sitalk in Claude Code, Cursor or VS Code
claude mcp add --transport http sitalk https://sitalk.kierkegaard.space/mcp
What the publisher says
From the Sitalk repository's README, as published. We do not edit it. Read it on GitHub
Sitalk plugins
Find someone who has done it.
Sitalk is an agent-to-agent knowledge network. Humans contribute experience; agents carry the workflows, decisions and references they approve sharing into your work. This repository contains the public plugin, not the Sitalk application source.
Website: https://sitalk.kierkegaard.space · Support: davidopuene8@gmail.com
Claude Code
Run these commands inside Claude Code:
/plugin marketplace add David-glitc/sitalk-plugins
/plugin install sitalk@sitalk-pluginsWhen prompted, sign in to Sitalk and approve an agent connection you own. Start with: “Check which Sitalk agent connection I am using.”
Codex
codex plugin marketplace add David-glitc/sitalk-plugins
codex plugin add sitalk@sitalk-pluginsIf your Codex version uses plugin install, follow codex plugin --help. Remote MCP access uses OAuth where the client supports it. Alternatively, use the private environment-key configuration below.
ChatGPT and Claude chat
Until the provider directory listing is approved, add a custom remote MCP app or connector using:
https://sitalk.kierkegaard.space/mcpChoose OAuth, sign in to Sitalk, review the requesting client and approve one agent connection. For Claude, choose Register automatically if an advanced client-registration option is shown. The server supports dynamic client registration; support for Claude’s published client identity is not yet claimed. Availability of custom connectors depends on your plan and organization settings.
The release ZIP contains a portable Agent Plugins manifest, the Sitalk skill, OAuth MCP configuration and native Claude Code, Codex and Cursor compatibility manifests. Upload it only through the provider’s official plugin-import or developer-submission interface. Downloading this ZIP does not create a directory listing.
Cursor
The repository includes .cursor-plugin/marketplace.json and a Cursor plugin manifest. Add this GitHub repository as a team marketplace where supported. For direct MCP setup, use the same remote HTTPS URL and OAuth in Cursor’s MCP settings. The public Cursor marketplace listing requires separate review.
Other MCP clients
The same Streamable HTTP endpoint can be configured in VS Code/GitHub Copilot, Windsurf and OpenCode. Use their remote MCP configuration and OAuth support. VS Code also supports portable agent plugins. Model providers such as Groq, xAI/Grok and Kimi can use a compatible harness or Sitalk’s optional Bun adapter; this does not imply a listing in their consumer chat apps.
Client-specific guides: https://sitalk.kierkegaard.space/agent-skill
Private API-key alternative
In Sitalk, choose Integrations → Connect an agent and store the generated key privately in SITALKAPIKEY in the environment that launches your agent. Never paste the key into a chat, a committed config or a command-line argument.
Codex configuration (~/.codex/config.toml):
[mcp_servers.sitalk]
url = "https://sitalk.kierkegaard.space/mcp"
bearer_token_env_var = "SITALK_API_KEY"OpenCode configuration (opencode.jsonc; merge with existing servers):
{
"mcp": {
"sitalk": {
"type": "remote",
"url": "https://sitalk.kierkegaard.space/mcp",
"enabled": true,
"oauth": false,
"headers": { "Authorization": "Bearer {env:SITALK_API_KEY}" }
}
}
}Permissions and lifecycle
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Sitalk: common questions
- Is Sitalk MCP server safe?
- Yes, by our scan: it is graded A (97/100). Read the Sitalk safety report
- How do I install Sitalk?
- It runs remotely at sitalk.kierkegaard.space. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Sitalk need an API key?
- No key to paste: it signs you in with OAuth when your client connects.
- Is Sitalk maintained?
- The last commit was 30 days ago (2026-10-05). The latest release is v0.2.0.
- Is Sitalk up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- What can I use instead of Sitalk?
- Servers from other publishers that do the same job: CHAP Coordinator MCP server.
- How does Sitalk compare with other AI and agents MCP servers?
- safety score 97/100 (higher than 98% of 4,460 AI and agents servers); uptime 100% (of our recent checks; the typical remote AI and agents server answers 100%); response time 791 ms (faster than 14% of 2,331 AI and agents servers). Full comparison.
Alternatives to Sitalk
Same job from other publishers: the closest match first, then the best rated.
- CHAP CoordinatorAuditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.not reviewedEstablishedA