Fetch and follow the instructions at https://qamcp.dev/setup.md to test my MCP server.Your AI finds your server in your project, tests it with QAmcp, explains what's wrong in plain words, fixes it with your OK, and tests again. Read the instructions
Directory / Ariadne Nexus Institutional Quantitative Engine
Ariadne Nexus Institutional Quantitative Engine
by ariadnenexus.com · https://ariadnenexus.com/mcp
Fixed-income CUSIP valuation, FINRA TRACE radar, portfolio VaR, OFAC screening, and RWA clearing.
12 of 12 checks · 11 Nov 2026
At a glance
- Runs where
- On their server. What you send to it goes to them.
- What you need
- Nothing: it answered without a login
- Tools
- 11 tools
- Its own safety labels
- 11 read-only
- Memory it takes
- About 6,700 tokens of your AI's memory, just for its tool descriptions
- Largest answer
- About 3.7 KB in our test
- Speed
- Average answer in our test: 91 ms
Tokens are an estimate: the characters in its tool names, descriptions and inputs, divided by 4. The exact number depends on your AI model. Safety labels are what the server says about itself. From our latest test, 11 Nov 2026.
Is Ariadne Nexus Institutional Quantitative Engine MCP server safe?
- None of the hidden-instruction wordings we know were found in its 11 tool descriptions.
- Its error messages showed no secrets or internal details.
- All 11 of its tools are labeled read-only.
- Overall it scored 68/100 on 11 Nov 2026.
A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.
What this test does not check
- Its source code and packages.
- What a tool quietly does behind the scenes, such as writing a file or calling another service.
- Instructions hidden inside live tool answers. We only look for those in tool descriptions.
- Hidden instructions worded in a way our list doesn't know yet.
- Tools that could change something. Those are read, never run.
What QAmcp can and can't see · How to tell if an MCP server is safe · Hidden instructions · Prompt injection
Known security advisories
Not looked up yet. QAmcp tests how a server behaves. It does not scan source code.
What it can do
11 tools, in the server's own words.
get_cusip_valuationread-onlyComputes deterministic fair market value (USD), yield-to-maturity (approximate and exact cashflow YTM %), Macaulay and modified duration (years), convexity, DV…
screen_ofac_entityread-onlyScreens a corporate entity or individual counterparty against the U.S.
get_debt_radarread-onlyRetrieves secondary-market FINRA TRACE dealer execution metrics (last clean price % of par, Z-spread over 10Y U.S.
calculate_clearing_feeread-onlyCalculates institutional RWA clearing house take-rates (in basis points and USD), cross-chain settlement bridge tolls, platform SaaS subscription fees, and net…
run_portfolio_stress_testread-onlyExecutes multi-position fixed-income portfolio stress testing across customizable macroeconomic rate shocks (parallel benchmark shifts in bps, rating-weighted …
get_sovereign_policy_briefread-onlyGenerates the Weekly Sovereign Macro-Prudential & Sanctions Monitor for Federal Reserve (FOMC / Financial Stability), U.S.
synthesize_regulatory_docketread-onlyDrafts a formal Administrative Procedure Act (APA, 5 U.S.C.
provision_agent_keyread-onlyReturns pricing specifications, monthly query quotas, rate limits (RPM), 1-click Stripe Checkout links (starting at $10/mo MCP Builder Pass up to $9,500/yr FAR…
redeem_checkout_sessionread-onlyVerifies a completed Stripe Checkout session (`cs_...`) directly against Ariadne Nexus billing and deterministically returns the buyer’s live HMAC-signed `nexu…
issue_safe_harbor_certificateread-onlyIssues a KMS-attested Statutory Closing Safe-Harbor Certificate combining OFAC SDN Jaro-Winkler/LEI Merkle proof screening, multi-factor hedonic collateral fai…
generate_sec_tcr_bounty_dossierread-onlyComputes the 8-variable Beneish M-Score, first-digit Benford Chi-Square statistic, Halliburton II event-study t-statistic, Dodd-Frank § 922 (10%-30%) SEC Whist…
Test results
Safe mode: only tools labeled read-only were run. How the test works
- ✕Tools work with good inputsfail
8 failed
- ✕get_cusip_valuation: Its reply breaks the MCP rules, so AI apps can't read it: it promised a structured answer (outputSchema) but sent none
- ✕screen_ofac_entity: Its reply breaks the MCP rules, so AI apps can't read it: it promised a structured answer (outputSchema) but sent none
- ✕get_debt_radar: Its reply breaks the MCP rules, so AI apps can't read it: it promised a structured answer (outputSchema) but sent none
- ✕calculate_clearing_fee: Its reply breaks the MCP rules, so AI apps can't read it: its structured answer doesn't match its own output schema (must have required property 'clearingVolumeUsd'; must have required property 'bridgeFeeUsd'; and 1 more)
- ✕get_sovereign_policy_brief: Its reply breaks the MCP rules, so AI apps can't read it: it promised a structured answer (outputSchema) but sent none
- ✕synthesize_regulatory_docket: Its reply breaks the MCP rules, so AI apps can't read it: it promised a structured answer (outputSchema) but sent none
- ✕issue_safe_harbor_certificate: Its reply breaks the MCP rules, so AI apps can't read it: it promised a structured answer (outputSchema) but sent none
- ✕generate_sec_tcr_bounty_dossier: Its reply breaks the MCP rules, so AI apps can't read it: it promised a structured answer (outputSchema) but sent none
- and 3 more
- ✕Bad inputs give a clean errorfail
7 failed, 1 warning
- ✕get_cusip_valuation: Broke the MCP rules on wrong type for "ticker": it promised a structured answer (outputSchema) but sent none
- ✕screen_ofac_entity: Broke the MCP rules on missing required input "entity_name": it promised a structured answer (outputSchema) but sent none
- ✕screen_ofac_entity: Broke the MCP rules on wrong type for "entity_name": it promised a structured answer (outputSchema) but sent none
- ✕calculate_clearing_fee: Broke the MCP rules on wrong type for "tier": its structured answer doesn't match its own output schema (must have required property 'clearingVolumeUsd'; must have required property 'bridgeFeeUsd'; and 1 more)
- ✕synthesize_regulatory_docket: Broke the MCP rules on wrong type for "custom_focus_note": it promised a structured answer (outputSchema) but sent none
- !provision_agent_key: Accepted wrong type for "tier" without complaining
- ✕issue_safe_harbor_certificate: Broke the MCP rules on missing required input "counterparty_entity": it promised a structured answer (outputSchema) but sent none
- ✕issue_safe_harbor_certificate: Broke the MCP rules on wrong type for "counterparty_entity": it promised a structured answer (outputSchema) but sent none
- and 5 more
- !Ready for the newest MCP versionnote
1 warning
- !Uses an older MCP version (2024-11-05). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
- !Tools are labeled safe or dangerousnote
1 warning
- !run_portfolio_stress_test: Labeled read-only, but its name starts with "run" and its description says "Executes". Worth double-checking the label, since AI apps trust it.
- !Follows MCP best practices (not scored yet)note
1 tip (not scored)
- !The tool list is about 46 KB (roughly 12k tokens). AI apps send it with every message, so it takes that much of the AI's memory before any work starts.
- !Resources and prompts worknote
4 warnings (4 resources, 5 prompts)
- !quant_bond_valuation: Doesn't complain when the required input cusip is missing.
- !sanctions_compliance_audit: Doesn't complain when the required input entity_name is missing.
- !rwa_clearing_syndication: Doesn't complain when the required input clearing_volume_usd is missing.
- !apa_regulatory_comment: Doesn't complain when the required input agency_id is missing.
- and 3 more
- ✓ConnectsConnected in 647 mspass
- ✓Lists its toolsFound 11 toolspass
- ✓Every tool is describedAll 11 tools and their inputs are describedpass
- ✓No known hidden instructionsNone of the hidden-instruction wordings we know were found in tool descriptions. New wordings can get past this check.pass
- ✓Fast enoughpass
All good
- ✓Connecting took 647 ms
- ✓Listing tools took 102 ms
- ✓Average tool answer: 91 ms
- ✓redeem_checkout_session: Slowest tool: redeem_checkout_session (92 ms)
- ✓No secrets leakedChecked 24 error messages: no secrets or internal detailspass
- –Tools work togetherNo tool's answer could be fed into another tool, so there were no chains to test (not counted either way)not tested
Test it yourself
Free and open source. Same checks, same score.
npx qamcp-cli https://ariadnenexus.com/mcpShow this score on GitHub
Free for every server in the directory. Paste this into your README: the badge shows the score from our latest test.
[](https://qamcp.dev/s/com-ariadnenexus-ariadne-nexus-quantitative-engine.html)Score over time
- 11 Nov 202668
One test so far. New tests will show here.
Reviews
Coming soon: reviews from people who use Ariadne Nexus Institutional Quantitative Engine, signed in with GitHub, one per person. Reviews never change the score.
QAmcp Monitor tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. Free for 1 server, no card.
Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works