HostVeritas Hosting Research
Server Details
Search and compare public hosting-provider facts with sources and explicit unknowns.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
Search, single-record fetch, and pairwise comparison are clearly distinct resource+action pairs with no overlap in intent. The descriptions reinforce the boundaries (search = find by filters, get = one canonical slug, compare = two or three providers in one category).
All three follow the same verb_noun snake_case pattern (search_providers, get_provider, compare_providers). No mixed conventions or stray casing.
Three tools are within a reasonable band and each earns its place as a read-only research surface. It is slightly thin, though: there is no tool for enumerating categories or locations, so discovery leans entirely on the search tool.
Search + get + compare covers the core read path and is coherent, but category and location filters require callers to already know valid values. Missing enumeration operations (e.g. list categories or location keys) are a notable gap that can cause dead ends for an agent.
Available Tools
3 toolscompare_providersCompare ProvidersARead-onlyIdempotentInspect
Compare two or three distinct published providers in one recorded service category. Reject the whole comparison if any profile is unavailable or lacks that category. Preserve unknown values and source evidence. Prices are approximate recorded USD monthly ranges, not budget-qualified quotes. Locations are provider-level candidates. No winner, quality, speed or compliance guarantee.
Inputs: slugs (required), category (required). Returns: rows, category, warnings, providers, +3 more
get_providerGet ProviderARead-onlyIdempotentInspect
Read one published provider by canonical slug. Returns public facts, evidence, explicit unknowns, approximate signup and renewal ranges, published-review aggregates and eligible endpoint uptime. Existing public field entitlements apply. Editorial availability is separate from customer reviews. Missing and hidden profiles return the same unavailable result.
Inputs: slug (required). Returns: provider, warnings, retrieved_at, schema_version
search_providersSearch ProvidersARead-onlyIdempotentInspect
Find published Free and paid providers alphabetically by literal name query, category and exact provider-location key. Locations are candidates, not confirmed service or plan availability. Default 10 results, maximum 20. Reuse the cursor with the same filters within 15 minutes; current records can change between pages. An empty result never relaxes filters.
Inputs: limit, query, cursor, category, +1 more. Returns: has_more, warnings, providers, next_cursor, +3 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Compare published AI solution rankings, company facts and research benchmarks with sources.
Is this person indexed on that data-broker domain? A three-state verdict, with the evidence.
Search observed public land listings and compare source-linked prices, evidence and freshness.
Search AI infrastructure, inspect facility evidence and explore sourced company relationships.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables read-only querying of inetGeek's sourced infrastructure data, returning provider facts with source sentences and URLs, comparisons, iScore rankings, and live DNS/SPF checks.3MIT
- AlicenseNot gradedqualityFmaintenanceVerifies claims with verdicts (supported/disputed/unverifiable), confidence scores, and cited sources by cross-referencing FoundryNet Data Network and web search.MIT
- AlicenseNot gradedqualityCmaintenanceEnables a calling LLM to ground its claims in raw observed facts by fetching claimed source URLs or running web searches, extracting atomic evidence, and logging provenance-stamped observations with fact IDs. It returns evidence rather than verdicts, so the model itself performs the comparison and its unverified gaps stay visible.1MIT
- AlicenseBqualityCmaintenanceEnables evidence-first company due diligence by resolving company identities, collecting verifiable facts with source URLs, timestamps, and payload hashes, flagging unverifiable dimensions, and generating auditable risk reports through MCP tools.10MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.