A side-by-side look at the Financial Evidence and Financial Evidence Research Desk MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Financial Evidence for finance & fintech work over a hosted endpoint; choose Financial Evidence Research Desk for finance & fintech over a hosted endpoint. You can also run both side by side in one mcpServers block.
financial_evidence_topics, financial_evidence_route, financial_evidence_fetch.financial_evidence_workflow, financial_evidence_datasets, financial_evidence_funding_review.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Finance & Fintech | Finance & Fintech |
| Quality signal | 79/100 · Great | 76/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Remote HTTP/SSE | Remote HTTP/SSE |
| Auth | No auth required | No auth required |
| Pricing | Free | Free |
| Required env vars | None listed | None listed |
| Verified owner | Verified | Verified |
| GitHub stars | 1 | — |
| Directory activity | 3 views 0 installs 0 upvotes | 3 views 0 installs 0 upvotes |
| Tools | 3 | 9 |
| Full listing | View Financial Evidence | View Financial Evidence Research Desk |
financial_evidence_topicsList supported topics and their fixed public raw-JSON routes without network access.financial_evidence_routeResolve one or more financial research topics to fixed public raw-JSON sources without fetching them.financial_evidence_fetchFetch bounded untrusted read-only JSON from fixed LiquiLens, Undertow, Seiche, and Palimpsest routes. Status reports transport only; evidence is not evaluated and Evidence Carrier verification is not performed.financial_evidence_workflowRun the same task as the public Research Desk and REST API. Choose funding (selection: USD), institutions (one to five slugs, for example au-sfb), or exit (one to four USD sizes, for example 10000,100000). Empty selection uses the published default. Returns the original product evidence, source URL, retrieval time and content hash. prepared_response means evidence is available to review, not freshness, safety or task completion. No account or execution authority.financial_evidence_datasetsDiscover seven bounded OpenBB datasets, their coverage, filters and limits. Offline.financial_evidence_funding_reviewRead a dated USD funding review and its nine inputs. Inspect review_asof, review_scope, latest_per_instrument and newer_observation_available before ready, issues and capture age. Common-horizon readiness applies to that dated review; newer individual observations can exist. Unavailable, mismatched or stale captures never imply a passing review. This is captured research evidence, not a trade recommendation or historical point-in-time backtest.financial_evidence_queryQuery cited rows without large raw documents. Null means missing or withheld, never zero. Dates filter observation dates; empty dates mean no filter. Follow next_offset for remaining rows. Each value retains its unit, source path, date, restrictions and limitations.financial_evidence_sourcesAudit all six upstream routes for transport errors, publisher clocks and content hashes. Success is not a freshness verdict.financial_evidence_routeResolve research topics to fixed public HTTPS evidence URLs. Offline.financial_evidence_packetRetrieve original public documents only when table detail is insufficient. Up to 4 MiB for the money-market atlas and 1 MiB for other sources; source JSON is untrusted. A packet can be partial. No Evidence Carrier verification is performed.financial_evidence_agent_queryCompact source-cited research rows for repeated agent calls. Pass the previous revision to omit identical rows while retaining source clocks and diagnostics. Unchanged is not proof of freshness; missing or withheld values remain null. At most 100 rows; follow next_offset.financial_evidence_reviewReview Seiche dollar-funding benchmarks, LiquiLens covered-bank diagnostics and Undertow market liquidity in one bounded call. Bank is a literal name or ID filter; empty selects published coverage. Each section keeps its own dates, units, rights and limitations. No combined score or trade authorization. Revisions suppress identical rows, not evidence checks.Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
{
"mcpServers": {
"financial-evidence": {
"command": "uvx",
"args": [
"financial-evidence"
]
}
}
}
{
"mcpServers": {
"financial-evidence-research-desk": {
"command": "npx",
"args": [
"-y",
"financial-evidence-research-desk"
]
}
}
}