Skip to main content
Glama

Startup Oracle

by io.github.pipeworx-io

Entity Profile

entity_profile
Read-onlyIdempotent

"Tell me about X" / "research Acme" / "brief me on Tesla" / "what does Apple do" / "company profile for Microsoft" / "give me the rundown on NVDA" / "everything you know about $TICKER" — full cross-source profile of a US public company in ONE parallel call. ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view. Fans out across SEC EDGAR, XBRL, USPTO patents, federal contracts (USAspending), FDA-licensed biologics (Purple Book), H-1B hiring (DOL LCA), news and GLEIF, and returns: cik + company_name (+ resolved_from/resolved_to when value was a name); recent_filings (up to 5 with pipeworx://edgar/company/{cik}/filings/{accession} URIs); fundamentals (LATEST 10-K Revenues + NetIncomeLoss + Cash, sorted period_end DESC); patents (USPTO PatentsView API sunset May 2025 — soft-fails until reactivated); federal_contracts (USAspending awards where the company is the recipient); fda_products (FDA-licensed biologics — vaccines, cell/gene therapies — from the Purple Book; a company with only small-molecule/generic drugs will show none here, that is expected, not a failure); hiring (H-1B sponsorship volume + salary range from DOL LCA filings); recent news mentions via GDELT→GNews fallback; LEI via GLEIF. sources_used / sources_failed say which of these actually returned data for THIS company — an empty section is a real "no data", not a bug. Pass a ticker ("AAPL"), zero-padded CIK ("0000320193"), OR a company name ("Moderna") — names now resolve via SEC EDGAR's company-name match; a private company (no CIK/ticker) returns resolved:false with an explicit notes line, not a bare failure. type accepts "company" or "ticker" interchangeably — both take the same value shapes above.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
typeYes"company" or "ticker" — both are accepted and behave identically; `value` can be a ticker, CIK, or company name either way. person/place coming soon.
valueYesTicker (e.g., "AAPL"), zero-padded CIK (e.g., "0000320193"), or company name (e.g., "Moderna") — names resolve via SEC EDGAR company-name match.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed3 schema fields changed
    • changedInput schema / properties / type / description
      Previous value: -"Entity type. Only \"company\" supported today; person/place coming soon."New value: +"\"company\" or \"ticker\" — both are accepted and behave identically; `value` can be a ticker, CIK, or company name either way. person/place coming soon."
    • changedInput schema / properties / type / enum
      Previous value: -[
-  "company"
-]New value: +[
+  "company",
+  "ticker"
+]
    • changedInput schema / properties / value / description
      Previous value: -"Ticker (e.g., \"AAPL\") or zero-padded CIK (e.g., \"0000320193\"). Names not supported — use resolve_entity first if you only have a name."New value: +"Ticker (e.g., \"AAPL\"), zero-padded CIK (e.g., \"0000320193\"), or company name (e.g., \"Moderna\") — names resolve via SEC EDGAR company-name match."
  2. Added

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, open-world, idempotent, and non-destructive behavior. The description adds substantial context beyond that: parallel fan-out, soft-fail on the USPTO PatentsView API sunset, expected empty sections, GDELT→GNews fallback, and resolved:false plus a notes line for private companies. This is far more than annotations alone provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long, but the tool is genuinely complex with many return sections and edge cases. It is dense and organized, though the 'ALWAYS PREFER' usage guidance could be front-loaded more aggressively, and a few phrases repeat information already present in the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description fully carries the burden of explaining the return structure, and it does so in detail: cik, recent_filings, fundamentals, patents, federal_contracts, fda_products, hiring, news, LEI, and sources_used/sources_failed. It also covers edge cases like API sunset soft-fails, empty sections, private companies, and expected absence of FDA biologics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description goes further by giving concrete examples ('AAPL', '0000320193', 'Moderna'), explaining that type is effectively interchangeable, and clarifying name resolution via SEC EDGAR. It slightly restates schema content, but the examples and edge-case notes add real value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states exactly what the tool does: builds a full cross-source profile of a US public company in one parallel call, with a concrete list of sources and return sections. Query examples make the trigger intent unmistakable, and the 'ALWAYS PREFER over chaining single-pack' phrasing distinguishes it from narrower lookups.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly tells the agent when to prefer this tool ('holistic view') and when not to rely on it (private companies return resolved:false; drug-only companies are expected to show no fda_products). The description also explains the accepted input shapes and what sources_failed/sources_used mean, leaving little to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Startup Oracle toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation2/5

ask_pipeworx_beta is explicitly identical to ask_pipeworx today, and ask_pipeworx_grounded is another variant of the same router, so an agent can easily misselect. Additionally, bet_research, polymarket_edges, and polymarket_arbitrage all present as prediction-market opportunity finders with overlapping responsibilities.

Naming Consistency3/5

Most tools follow snake_case verb_noun (ask_pipeworx, list_subscriptions, resolve_entity, unsubscribe, validate_claim), but several break the pattern with noun phrases like polymarket_edges and pipeworx_trending, plus oddities like startup_oracle_evaluate. The mix is readable but not predictable.

Tool Count2/5

32 tools is well over the 25 threshold and the set is not tightly scoped: prediction markets alone account for six overlapping tools, and the server also bundles memory, subscriptions, npm dependency scanning, llms.txt generation, and AI visibility checks. ask_pipeworx_beta adds a duplicate that does not earn its slot.

Completeness3/5

As a read-heavy research gateway, the surface is broad: lookups, profiles, comparisons, verification, deep research, discovery, and citation handling are covered, and the subscription/memory helpers have their own lifecycle operations. But the 'Startup Oracle' mission is thin — startup-specific evaluation is a single joke tool, and there is no way to update subscriptions or act on research findings beyond saving memory.

Resources