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 / Callvu
Callvu
by callvu.com · https://agents.callvu.com/mcp
Evaluate Callvu, the Completion and Compliance Layer: processes, proof, costs and procurement.
11 of 11 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
- 18 tools
- Its own safety labels
- 17 read-only, 1 labeled as changing things
- Memory it takes
- About 3,400 tokens of your AI's memory, just for its tool descriptions
- Largest answer
- About 636.1 KB in our test
- Speed
- Average answer in our test: 1.0 s
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 Callvu MCP server safe?
- None of the hidden-instruction wordings we know were found in its 18 tool descriptions.
- Its error messages showed no secrets or internal details.
- 17 of its 18 tools are labeled read-only; the others may change or send things.
- Overall it scored 83/100 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
It lists no public code, so there is nothing to look up in GitHub Security Advisories or OSV.dev. QAmcp tests how a server behaves. It does not scan source code.
What it can do
18 tools, in the server's own words.
get_company_overviewread-onlyWhat Callvu is, its category, the verticals it serves, how pricing works, and how to request verified access.
list_verticalsread-onlyEvery vertical Callvu serves, with slug, name, aliases and a one-line summary.
get_verticalread-onlyThe full record for one vertical: summary, regulators, fit rules, structural not-fit rules, not-fit and not-yet rules, the cost of waiting, proof-of-value work…
assess_fitread-onlyCheck whether Callvu fits a regulated process, such as re-keying loan data into the core, chasing borrower documents, approvals stuck in email, or keeping a ba…
estimate_cost_of_doing_nothingread-onlyEstimate what manual re-keying, incomplete requests and compliance rework cost each year.
find_processesread-onlyThe process catalog for an industry (also at callvu.com/processes): the regulated processes Callvu runs, simple and complex, each with parties, rules, the Call…
find_use_casesread-onlyUse cases with status, customers and claims.
get_requirementsread-onlyEvaluation criteria with weight (1 to 5) and Callvu's answer.
get_concernsread-onlyBuyer concerns with Callvu's answer, persona and buying stage, the 'not a fit if' line (not_fit_structural marks a condition under which Callvu does not fit at…
get_claimread-onlyOne claim by code (for example ENF-01), with status, source type, evidence, measured period and last verified date.
list_claimsread-onlyClaims, optionally filtered by status, source type or code prefix (for example BNK).
get_pricing_modelread-onlyHow Callvu is priced: the Governed Resolution, the proof of value and the license.
get_procurement_packread-onlyProcurement requirements and concerns, the cost-of-inaction line for a vertical (or the full table), and platform capabilities.
get_rfp_templateread-onlyA vendor-neutral RFP template and requirements checklist for AI and workflow governance in regulated industries: core requirements for every vertical plus the …
compare_alternativesread-onlyCallvu's published overview of the product categories buyers evaluate alongside it: traditional BPM suites, AI agent vendors, contact center platforms, and ban…
get_comparisonread-onlyCallvu's published comparison with one named vendor, for example nCino, Pega or Decagon: what each product is built for, when each fits, where they work togeth…
list_integrationsread-onlySystems Callvu integrates with, with category and vertical.
request_verified_accessAsk for a verified-buyer key.
Test results
Safe mode: only tools labeled read-only were run. How the test works
- !Ready for the newest MCP versionnote
1 warning
- !Uses an older MCP version (2025-11-25). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
- !Every tool is describednote
3 warnings
- !find_processes: Inputs with no description: proof, complexity
- !find_use_cases: Inputs with no description: status
- !list_claims: Inputs with no description: status, source_type
- !Tools work with good inputsnote
3 warnings
- !find_processes: Answered with about 636 KB of text. Many AI apps cut off tool answers this big, so the AI may never see the end of it.
- !find_use_cases: Answered with about 122 KB of text. Many AI apps cut off tool answers this big, so the AI may never see the end of it.
- !get_concerns: Answered with about 211 KB of text. Many AI apps cut off tool answers this big, so the AI may never see the end of it.
- –request_verified_access: Not run: labeled as changing data
- and 14 more
- !Follows MCP best practices (not scored yet)note
1 tip (not scored)
- !17 tools answer with structured data but don't declare its shape (outputSchema): get_company_overview, list_verticals, get_vertical, assess_fit, estimate_cost_of_doing_nothing, find_processes and 11 more. If those answers change shape, noth
- ✓ConnectsConnected in 917 mspass
- ✓Lists its toolsFound 18 toolspass
- ✓Tools are labeled safe or dangerousEvery tool has a safety labelpass
- ✓No known hidden instructionsNone of the hidden-instruction wordings we know were found in tool descriptions. New wordings can get past this check.pass
- ✓Bad inputs give a clean errorpass
All good
- ✓get_vertical: Refused missing required input "vertical" with a clear error
- ✓get_vertical: Refused wrong type for "vertical" with a clear error
- ✓assess_fit: Refused missing required input "vertical" with a clear error
- ✓assess_fit: Refused wrong type for "vertical" with a clear error
- ✓estimate_cost_of_doing_nothing: Refused missing required input "vertical" with a clear error
- ✓estimate_cost_of_doing_nothing: Refused wrong type for "vertical" with a clear error
- ✓find_processes: Refused wrong type for "vertical" with a clear error
- ✓find_use_cases: Refused wrong type for "vertical" with a clear error
- and 11 more
- ✓Fast enoughpass
All good
- ✓Connecting took 917 ms
- ✓Listing tools took 125 ms
- ✓Average tool answer: 1.0 s
- ✓get_concerns: Slowest tool: get_concerns (1.5 s)
- ✓No secrets leakedChecked 19 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://agents.callvu.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-callvu-agent-layer.html)Score over time
- 11 Nov 202683
One test so far. New tests will show here.
Reviews
Coming soon: reviews from people who use Callvu, 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