In-depth architectural comparison of the Hledger MCP and Financial Evidence Research Desk MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Hledger MCP
Finance & Fintech · Local stdio
Quality: 59/100 (Good) | Auth: No auth required
Financial Evidence Research Desk
Finance & Fintech · Remote HTTP/SSE
Quality: 76/100 (Great) | Auth: No auth required
Verdict Summary: Choose Hledger MCP if you need specialized Finance & Fintech tools running via a local process. Choose Financial Evidence Research Desk if your workspace requires Finance & Fintech integration with remote web transport. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Hledger MCP when:
You need dedicated capabilities in the Finance & Fintech domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
You have access to required keys: HLEDGER_READ_ONLY, HLEDGER_SKIP_BACKUP, HLEDGER_EXECUTABLE_PATH, HLEDGER_WEB_EXECUTABLE_PATH.
Double entry plain text accounting, right in your LLM! This MCP enables comprehensive read, and (optional) write access to your local HLedger accounting journals.
Eight read-only MCP tools for paginated financial research: bank disclosures, funding benchmarks and history, liquidity evidence and source health. Seven dataset views retain sources, observation dates, units and unavailable values. Public access requires no API key. Hosted at /openbb/mcp; distinct from the three-tool Financial Evidence source router. Includes a browser desk, REST/OpenAPI and CSV examples. LIQUILENS PRIVATE LIMITED; source-specific rights and partial coverage apply.
Tools & Capabilities Breakdown
Hledger MCP Tools (4)
txt
csv
json
html
Financial Evidence Research Desk Tools (8)
financial_evidence_datasets
Discover seven bounded OpenBB datasets, their coverage, filters and limits. Offline.
financial_evidence_funding_review
Read 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.
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Hledger MCP is categorized under Finance & Fintech and uses a local stdio subprocess. In contrast, Financial Evidence Research Desk belongs to Finance & Fintech using remote streaming HTTP/SSE transport. Select Hledger MCP when you need capabilities focused on finance & fintech and Financial Evidence Research Desk when you require tools for finance & fintech.
Query 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_sources
Audit all six upstream routes for transport errors, publisher clocks and content hashes. Success is not a freshness verdict.
financial_evidence_route
Resolve research topics to fixed public HTTPS evidence URLs. Offline.
financial_evidence_packet
Retrieve 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_query
Compact 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_review
Review 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.