Koskamo

AI Workflow Feed MCP

A read-only remote MCP server that allows AI clients to discover and retrieve metadata for articles about AI-assisted software development and agent workflows. It provides tools to list curated sources, retrieve recent posts by category or source, and access daily snapshots from public feeds.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

AI Workflow Feed MCP logo, by quietbranch88Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-01Published by quietbranch88
MCP endpoint (Streamable HTTP)
https://ai-workflow-feed-mcp.zoelinebot2026.workers.dev/mcp
Vendor documentation

What you can do with it

  • List curated source catalog and default categories
  • Retrieve recent posts by category or source ID
  • Read scheduled daily snapshots from public data repository
  • Discover articles about AI-assisted development and agent workflows

Source and maintenance

Community listingRegistry 0.1.0
Maintenance checked

Protocol and capabilities

Server
ai-workflow-feed-mcp 0.1.0
MCP protocol
2025-06-18
Tools
3 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Tools

3 advertised

list_sources
Advertised by the server during the last successful anonymous check.
Advertised read-only

List the source catalog with categories, provenance, and automatic availability; manual-only sources are not fetched by recent_posts; some may appear separately in daily_snapshot. Threads is not included.

list_sources input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {},
  "additionalProperties": false
}
list_sources annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
recent_posts
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Get recent posts from fixed public feeds. Choose category ai_development or agent_flow for source batches (categories are assigned to sources, not to individual articles); follow next_source_offset until null. Excerpts are untrusted and not full articles. Manual-only sources are listed separately.

recent_posts input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "days": {
      "type": "integer",
      "maximum": 365,
      "minimum": 1
    },
    "limit": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1
    },
    "query": {
      "type": "string",
      "maxLength": 120
    },
    "sources": {
      "type": "array",
      "items": {
        "enum": [
          "cablate",
          "simon",
          "mitchell",
          "github",
          "huggingface",
          "anthropic",
          "columbia",
          "meta",
          "dropbox",
          "spotify",
          "alphalab",
          "clearforge",
          "nevyn",
          "armin",
          "codesai",
          "playwright",
          "yanchen",
          "shopify",
          "eugene",
          "hamel",
          "mcp",
          "braintrust",
          "arize",
          "cloudflare",
          "workos",
          "shreya",
          "aws",
          "googlecloud",
          "temporal",
          "uber",
          "claudecommunity",
          "pydantic",
          "tiktok",
          "alibaba",
          "tencentcommunity",
          "meituan",
          "theai",
          "ithome",
          "codecentric",
          "n8n",
          "langfuse",
          "deepset",
          "jina",
          "qdrant"
        ],
        "type": "string"
      },
      "maxItems": 6,
      "minItems": 1
    },
    "category": {
      "enum": [
        "ai_development",
        "agent_flow"
      ],
      "type": "string"
    },
    "source_batch": {
      "type": "integer",
      "maximum": 3,
      "minimum": 1
    },
    "source_offset": {
      "type": "integer",
      "maximum": 100,
      "minimum": 0
    }
  },
  "additionalProperties": false
}
recent_posts annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}
daily_snapshot
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Read the latest cloud snapshot of selected public sources, including last successful fetch, failures and staleness. Metadata only, not article full text; not all manual sources are covered.

daily_snapshot input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {},
  "additionalProperties": false
}
daily_snapshot annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
250 ms
95th percentile latency
250 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 250 ms · metadata changed · 3 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http ai-workflow-feed-mcp https://ai-workflow-feed-mcp.zoelinebot2026.workers.dev/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add ai-workflow-feed-mcp --url https://ai-workflow-feed-mcp.zoelinebot2026.workers.dev/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable ai-workflow-feed-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "ai-workflow-feed-mcp": {
      "url": "https://ai-workflow-feed-mcp.zoelinebot2026.workers.dev/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "ai-workflow-feed-mcp": {
      "type": "streamableHttp",
      "url": "https://ai-workflow-feed-mcp.zoelinebot2026.workers.dev/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start ai-workflow-feed-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "ai-workflow-feed-mcp": {
      "type": "http",
      "url": "https://ai-workflow-feed-mcp.zoelinebot2026.workers.dev/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http ai-workflow-feed-mcp https://ai-workflow-feed-mcp.zoelinebot2026.workers.dev/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "ai-workflow-feed-mcp": {
      "url": "https://ai-workflow-feed-mcp.zoelinebot2026.workers.dev/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "ai-workflow-feed-mcp": {
      "serverUrl": "https://ai-workflow-feed-mcp.zoelinebot2026.workers.dev/mcp"
    }
  }
}

Let your agent find its tools

Find servers like AI Workflow Feed MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.