Cobalt
Server Details
Cobalt Intelligence MCP — US Secretary-of-State business registration, UCC
Glama couldn't complete the latest health check. 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
- 0.2% over 24 days
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- pipeworx-io/mcp-cobalt
- GitHub Stars
- 0
- Server Listing
- cobalt
TDQS
Scored across 39 tools
Multiple tools have overlapping research/router purposes: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, discover_tools, suggest_questions, and validate_claim all answer or route general questions, while polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, and bet_research overlap heavily on finding market opportunities. The exhaustive descriptions try to disambiguate, but the boundaries remain blurry enough that agents could easily misselect.
All names use snake_case, which keeps them readable, but the set mixes several prefixes (cobalt_, polymarket_, pipeworx_, ask_pipeworx_) with both verb-based names (remember, recall, forget, subscribe) and noun-based names (entity_profile, company_facts, resolution_audit). There is no single predictable verb_noun pattern, though the convention is not chaotic.
39 tools is heavy for a single MCP server, especially given the overlapping meta-tools and multiple Polymarket analysis variants. The apparent scope is broad but does not obviously require this many distinct tools, and several could be consolidated.
The set covers many domains broadly, with generic routers that can work around missing direct lookups, plus CRUD-ish coverage for memory and subscriptions. However, there are notable gaps and dead ends: no update operation for subscriptions, no direct fetch tool for many referenced data sources, and explicit unsupported areas such as court release calendars and non-NPM dependency scanning.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
7 tool updates
- Changed
ask_pipeworx3 fields changed- added
Input schema / properties / askAdded value: +{ + "description": "Alias for question.", + "type": "string" +} - added
Input schema / properties / messageAdded value: +{ + "description": "Alias for question.", + "type": "string" +} - changed
Input schema / properties / question / descriptionPrevious value: -"Your question or request in natural language. Accepts query, q, prompt, text, input as aliases."New value: +"Your question or request in natural language. Accepts query, q, prompt, text, input, ask, message as aliases."
- Changed
ask_pipeworx_beta3 fields changed- added
Input schema / properties / askAdded value: +{ + "description": "Alias for question.", + "type": "string" +} - added
Input schema / properties / messageAdded value: +{ + "description": "Alias for question.", + "type": "string" +} - changed
Input schema / properties / question / descriptionPrevious value: -"Your question or request in natural language. Accepts query, q, prompt, text, input as aliases."New value: +"Your question or request in natural language. Accepts query, q, prompt, text, input, ask, message as aliases."
- Changed
ask_pipeworx_grounded3 fields changed- added
Input schema / properties / askAdded value: +{ + "description": "Alias for question.", + "type": "string" +} - added
Input schema / properties / messageAdded value: +{ + "description": "Alias for question.", + "type": "string" +} - changed
Input schema / properties / question / descriptionPrevious value: -"Your question in natural language. Accepts query, q, prompt, text, input as aliases."New value: +"Your question in natural language. Accepts query, q, prompt, text, input, ask, message as aliases."
- Changed
deep_research8 fields changed- added
Input schema / properties / askAdded value: +{ + "description": "Alias for question.", + "type": "string" +} - added
Input schema / properties / inputAdded value: +{ + "description": "Alias for question.", + "type": "string" +} - added
Input schema / properties / messageAdded value: +{ + "description": "Alias for question.", + "type": "string" +} - added
Input schema / properties / promptAdded value: +{ + "description": "Alias for question.", + "type": "string" +} - added
Input schema / properties / qAdded value: +{ + "description": "Alias for question.", + "type": "string" +} - added
Input schema / properties / queryAdded value: +{ + "description": "Alias for question.", + "type": "string" +} - changed
Input schema / properties / question / descriptionPrevious value: -"The research question, in natural language. Broad/multi-part is fine — decomposition is the point."New value: +"The research question, in natural language. Broad/multi-part is fine — decomposition is the point. Accepts query, q, prompt, text, input, ask, message as aliases." - added
Input schema / properties / textAdded value: +{ + "description": "Alias for question.", + "type": "string" +}
- Changed
forget4 fields changed- added
Input schema / properties / kAdded value: +{ + "description": "Alias for key.", + "type": "string" +} - changed
Input schema / properties / key / descriptionPrevious value: -"Memory key to delete"New value: +"Memory key to delete. Accepts name, k, label as aliases." - added
Input schema / properties / labelAdded value: +{ + "description": "Alias for key.", + "type": "string" +} - added
Input schema / properties / nameAdded value: +{ + "description": "Alias for key.", + "type": "string" +}
- Changed
recall4 fields changed- added
Input schema / properties / kAdded value: +{ + "description": "Alias for key.", + "type": "string" +} - changed
Input schema / properties / key / descriptionPrevious value: -"Memory key to retrieve (omit to list all keys)"New value: +"Memory key to retrieve (omit to list all keys). Accepts name, k, label as aliases." - added
Input schema / properties / labelAdded value: +{ + "description": "Alias for key.", + "type": "string" +} - added
Input schema / properties / nameAdded value: +{ + "description": "Alias for key.", + "type": "string" +}
- Changed
remember9 fields changed- added
Input schema / properties / contentAdded value: +{ + "description": "Alias for value.", + "type": "string" +} - added
Input schema / properties / dataAdded value: +{ + "description": "Alias for value.", + "type": "string" +} - added
Input schema / properties / kAdded value: +{ + "description": "Alias for key.", + "type": "string" +} - changed
Input schema / properties / key / descriptionPrevious value: -"Memory key (e.g., \"subject_property\", \"target_ticker\", \"user_preference\")"New value: +"Memory key (e.g., \"subject_property\", \"target_ticker\", \"user_preference\"). Accepts name, k, label as aliases." - added
Input schema / properties / labelAdded value: +{ + "description": "Alias for key.", + "type": "string" +} - added
Input schema / properties / nameAdded value: +{ + "description": "Alias for key.", + "type": "string" +} - added
Input schema / properties / textAdded value: +{ + "description": "Alias for value.", + "type": "string" +} - added
Input schema / properties / vAdded value: +{ + "description": "Alias for value.", + "type": "string" +} - changed
Input schema / properties / value / descriptionPrevious value: -"Value to store (any text — findings, addresses, preferences, notes)"New value: +"Value to store (any text — findings, addresses, preferences, notes). Accepts content, text, data, v as aliases; a non-string value is stored as JSON."
22 tool updates
- Changed
ai_visibility_check1 field changed- added
Input schema / examplesAdded value: +[ + { + "entity": "Tesla" + } +]
- Changed
ask_pipeworx_beta1 field changed- added
Input schema / examplesAdded value: +[ + { + "question": "What is the current US unemployment rate?" + } +]
- Changed
ask_pipeworx_grounded1 field changed- added
Input schema / examplesAdded value: +[ + { + "question": "What was Apple's fiscal 2023 revenue?" + } +]
- Changed
company_facts5 fields changed- added
Input schema / examplesAdded value: +[ + { + "attribute": "revenue", + "company": "AAPL", + "period": { + "fiscal_year": 2023, + "type": "annual" + } + } +] - added
Input schema / properties / as_ofAdded value: +{ + "description": "Past ISO timestamp with timezone. Replay the latest answer actually recorded by that instant; no invented history or live fallback.", + "type": "string" +} - added
Input schema / properties / exclude_publishersAdded value: +{ + "description": "Publisher ids forbidden for fact retrieval: sec, fmp, alphavantage. Case and surrounding whitespace are normalized; unknown ids are refused. Excluding sec currently leaves no eligible fact source and returns unavailable/sources_excluded with the selection reasons. Identity and fiscal-calendar lookups may still use SEC; no excluded financial concept is fetched.", + "items": { + "type": "string" + }, + "type": "array" +} - added
Input schema / properties / freshnessAdded value: +{ + "description": "cached (default) permits an eligible stored answer; fresh requires an upstream refresh and never silently falls back to stale data.", + "enum": [ + "cached", + "fresh" + ], + "type": "string" +} - added
Input schema / properties / max_ageAdded value: +{ + "description": "Maximum age in seconds of the upstream publication, not our fetch. Older or undated facts are withheld.", + "maximum": 3155760000, + "minimum": 0, + "type": "number" +}
- Changed
compare_entities1 field changed- added
Input schema / examplesAdded value: +[ + { + "type": "company", + "values": [ + "AAPL", + "MSFT" + ] + } +]
- Changed
deep_research1 field changed- added
Input schema / examplesAdded value: +[ + { + "depth": "quick", + "question": "What is the current US unemployment rate and how has it changed over the past year?" + } +]
- Changed
entity_profile1 field changed- added
Input schema / examplesAdded value: +[ + { + "type": "company", + "value": "AAPL" + } +]
- Changed
generate_llms_txt1 field changed- added
Input schema / examplesAdded value: +[ + { + "url": "https://pipeworx.io" + } +]
- Changed
pipeworx_feedback1 field changed- added
Input schema / examplesAdded value: +[ + { + "message": "Fleet #2184 smoke test: verifying pipeworx_feedback example call returns non-empty.", + "type": "other" + } +]
- Changed
pipeworx_trending1 field changed- added
Input schema / examplesAdded value: +[ + { + "window": "7d" + } +]
- Changed
polymarket_arbitrage1 field changed- added
Input schema / examplesAdded value: +[ + { + "topic": "Fed rate decision" + } +]
- Changed
polymarket_edge_tracker1 field changed- added
Input schema / examplesAdded value: +[ + { + "days": 14, + "window": "1wk" + } +]
- Changed
polymarket_edges3 fields changed- added
Input schema / examplesAdded value: +[ + { + "limit": 5, + "window": "1wk" + } +] - changed
Input schema / properties / min_edge_pp / descriptionPrevious value: -"Minimum |edge| in percentage points to include (default 0.5). Edge is evaluated NET of slippage."New value: +"Minimum |edge| in percentage points to include (default 0.5). Edge is evaluated NET of slippage and Polymarket's own taker fee." - changed
Input schema / properties / slippage_pp / descriptionPrevious value: -"Assumed execution slippage in percentage points per leg (default 0.3). Subtracted from raw |edge| before ranking and Kelly sizing. Polymarket has zero trading fees as of 2024 but bid/ask + thin depth typically eats 20-50bp per trade. Bump for very thin partitions; drop to 0 if you have a smarter fill model."New value: +"Assumed execution slippage in percentage points per leg (default 0.3), for bid/ask + thin depth cost that a last-trade price does not show. Subtracted from raw |edge| before ranking and Kelly sizing, ON TOP OF Polymarket's own taker fee — which is NOT zero (rate 0.04-0.07 depending on category, read off each market's own published fee schedule; see fees_pp_applied on every row and fees.ts for the full schedule). Bump slippage for very thin partitions; drop to 0 if you have a smarter fill model — the fee still applies regardless."
- Changed
polymarket_fill_risk1 field changed- added
Input schema / examplesAdded value: +[ + { + "market": "will-the-fed-increase-interest-rates-by-25-bps-after-the-december-2026-meeting-20260729232808636", + "side": "buy_yes", + "size_usd": 1000 + } +]
- Changed
recent_changes1 field changed- added
Input schema / examplesAdded value: +[ + { + "since": "30d", + "type": "company", + "value": "AAPL" + } +]
- Changed
remember1 field changed- added
Input schema / examplesAdded value: +[ + { + "key": "target_ticker", + "value": "AAPL" + } +]
- Changed
resolve_entity1 field changed- added
Input schema / examplesAdded value: +[ + { + "type": "company", + "value": "AAPL" + } +]
- Changed
scan_competitor_ai_presence1 field changed- added
Input schema / examplesAdded value: +[ + { + "entities": [ + "Pipeworx", + "Zapier" + ] + } +]
- Changed
scan_dependency1 field changed- added
Input schema / examplesAdded value: +[ + { + "package": "left-pad" + } +]
- Changed
search_within1 field changed- added
Input schema / examplesAdded value: +[ + { + "query": "supply-chain risk", + "text": "Apple Inc. reported fiscal 2023 revenue of $383.285 billion, driven by strong iPhone and Services growth. Net income was $96.995 billion. The company faced supply-chain risk in China during the quarter." + } +]
- Changed
suggest_questions1 field changed- added
Input schema / examplesAdded value: +[ + { + "topic": "finance" + } +]
- Changed
validate_claim1 field changed- added
Input schema / examplesAdded value: +[ + { + "claim": "Apple's fiscal 2023 revenue was $383 billion" + } +]
39 tool updates
- First observed
ai_visibility_check - First observed
ask_pipeworx - First observed
ask_pipeworx_beta - First observed
ask_pipeworx_grounded - First observed
bet_research - First observed
cobalt_business_search - First observed
cobalt_tin_verify - First observed
cobalt_ucc - First observed
company_facts - First observed
compare_entities - First observed
deep_research - First observed
discover_tools - First observed
entity_profile - First observed
forget - First observed
generate_llms_txt - First observed
kalshi_weather_edge - First observed
list_subscriptions - First observed
pipeworx_feedback - First observed
pipeworx_trending - First observed
polymarket_arbitrage - First observed
polymarket_edge_tracker - First observed
polymarket_edges - First observed
polymarket_fill_risk - First observed
polymarket_kalshi_spread - First observed
recall - First observed
recent_alerts - First observed
recent_changes - First observed
release_calendar_markets - First observed
remember - First observed
resolution_audit - First observed
resolution_diff - First observed
resolve_entity - First observed
scan_competitor_ai_presence - First observed
scan_dependency - First observed
search_within - First observed
subscribe - First observed
suggest_questions - First observed
unsubscribe - First observed
validate_claim
Related MCP Connectors
OpenCorporates MCP — Global company registry data (BYO key)
US public-records intelligence for AI agents — companies, SEC, courts, spending, licenses.
Confirm a US business is real and find who controls it. 32.6M official registry records.
Companies House MCP — UK statutory company registry (BYO key)
Related MCP Servers
AlicenseAqualityDmaintenanceEnables AI agents to verify and search business entities across US state and international company registries, providing real-time confirmation of legal existence, status, and filings.9MIT- AlicenseNot gradedqualityCmaintenanceAggregate US business filings, SEC reports, federal court cases, federal spending awards, and professional licenses through a single MCP server.1MIT
- AlicenseAqualityBmaintenanceExposes 29 official business-registry actors as MCP tools for KYC/AML, beneficial-owner (UBO), credit-risk and adverse-media workflows across 11 jurisdictions (EU, US, UAE). Sourced via Apify; pay-per-result.386MIT

whetstone-mcpofficial
AlicenseAqualityDmaintenanceAn MCP server for U.S. public-records data, enabling AI agents to search business registrations, screen names against government watchlists, and pull federal awards.440 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.