Ai Feeds
Server Details
AI Feeds MCP.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 0.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- pipeworx-io/mcp-ai-feeds
- GitHub Stars
- 0
- Server Listing
- mcp-ai-feeds
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 47 tools
Several clusters have unclear boundaries: ask_pipeworx / ask_pipeworx_beta / ask_pipeworx_grounded are three routers whose own descriptions admit beta is currently identical to the stable one, and the prediction-market surface (polymarket_edges, polymarket_arbitrage, polymarket_edge_tracker, polymarket_fill_risk, kalshi_weather_edge, polymarket_kalshi_spread, updown_venue_compare, bet_research, release_calendar_markets) offers nine tools an agent must disambiguate on subtle grounds. research_row / classify_row / validate_claim / ask_pipeworx_grounded also overlap around 'extract a verified answer', and discover_tools vs suggest_questions both serve tool discovery. Descriptions do a lot of rescue work, but the agent must read paragraphs to choose correctly.
All names are snake_case, which keeps it readable, but the conventions are mixed: some are verb_noun (get-style implied: fetch_feed, read_feed, list_feeds, resolve_entity, compare_entities, validate_claim, generate_llms_txt, discover_tools) while many are bare noun phrases (company_facts, entity_profile, prediction_calibration, recent_alerts, resolution_audit, recent_changes, pipeworx_trending). Prefixing is also inconsistent — polymarket_* and updown_* are namespaced by venue/domain, but ask_pipeworx, bet_research and kalshi_weather_edge are not, so grouping cannot be inferred from the name alone.
47 tools is far past the point where an agent can hold the surface in context, and the server is labelled 'Ai Feeds' while the bulk of the catalog is SEC/XBRL financials, prediction-market arbitrage and web-archive forensics. Even accepting a broad gateway scope, several entries are marginal (ask_pipeworx_beta duplicates the stable router, pipeworx_trending and pipeworx_feedback are meta rather than data tools), which inflates the count without adding capability.
Within the individual sub-domains coverage is genuinely deep: entity resolution, typed financial facts, prediction-market pricing/fill/calibration, archives, feeds, memory and subscriptions all have multi-step lifecycle support (remember/recall/forget, subscribe/list/unsubscribe/recent_alerts). The notable gaps are cross-cutting: no generic URL fetch or web search primitive despite several tools depending on fetching, no batch/queue tool for running research_row across many rows (it only 'composes with batch callers'), and no update path for stored memory or subscriptions beyond delete/recreate.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceControl AI agents creation and modification via MCP.-
- AlicenseAqualityBmaintenanceMCP server for ffl. Let AI share anything for you.115Apache 2.0
- AlicenseAqualityCmaintenanceAI Gateway - MCP server providing AI-powered tools and automation by MEOK AI Labs419 npm141 PyPIMIT
- MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.