@qverisai/mcp
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Contacts while installing and starting: nothing
What it contacted
Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.
Starting it
npx -y @qverisai/mcp@0.15.1
Installing a package runs its code. Use a sandbox for anything you have not read.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
discover query, limit, session_id, view, lang
Discover available tools when task fit, data quality/freshness, provider comparison, fallback, or the user request favors QVeris. QVeris is not a mandatory gateway. Returns relevant tools that can help accomplish tasks. Provider comparison: Inspect each candidate to confirm current scope/contracts; Probe each when current quotes are required. Call a sufficiently detailed result directly; inspection is optional. Results may include billing_rule metadata for rule-level pricing.
inspect tool_ids, search_id, session_id
Optionally inspect tools by ID when selection or valid request construction depends on missing/stale contract details. Provider comparison: Inspect each candidate to confirm current scope/contracts; Probe each when current quotes are required. Returns parameters, success rate, latency, examples, and billing_rule when available. For a public-to-authenticated continuation, retain the selected tool_id and omit the public search_id. Use the returned authenticated context for Call.
probe sub_user_id, tool_id, parameters, checks, live_budget
Optionally validate parameters or obtain a zero-cost quote when inputs are uncertain, a current quote is needed for a budget decision, or preflight is explicitly requested. Probe is not required before Call, never executes the capability, and does not reserve a price or grant authorization. Schema and quote are implemented; coverage and sample may return an explicit unknown verdict.
call sub_user_id, tool_id, search_id, params_to_tool, session_id, model, max_response_size, respond_with, require_zero_quote
Call a specific remote tool with provided parameters. Use a tool_id and current authenticated search_id from Discover or Inspect. A public search_id cannot be used for Call. Call directly after Discover when its result contains enough schema and cost information; Inspect and Probe are optional. Pass parameters to the tool through params_to_tool. Set require_zero_quote=true to require a current exact zero-credit quote before the server dispatches the Call. For uncertain outcomes, use the returned idempotency_key with lookup_execution; keys are issued by the host client and lookup never submits a new Call. Reuse only exact routes; rebuild current parameters and Call again for current/latest/today/time-sensitive data. The response may include pre-settlement billing; use usage_history or credits_ledger for final charge status.
lookup_execution idempotency_key
Read-only lookup for a prior Call by its exact idempotency key. It never submits or retries a Call.
5 more tools
usage_history mode, start_date, end_date, bucket, execution_id, search_id, event_type, kind, success, charge_outcome, min_credits, max_credits, limit
Context-safe usage audit query. Defaults to aggregated summary, supports precise search by execution_id/search_id/charge_outcome/credit range, and writes large exports to a local JSONL file instead of returning all rows.
credits_ledger mode, start_date, end_date, bucket, entry_type, direction, min_credits, max_credits, limit
Context-safe final credits ledger query. Defaults to aggregated summary, supports precise search by entry type/direction/credit range, and writes large exports to a local JSONL file instead of returning all rows.
search_tools query, limit, session_id, view, lang
[Deprecated: use "discover" instead] Discover available tools when task fit, data quality/freshness, provider comparison, fallback, or the user request favors QVeris. QVeris is not a mandatory gateway. Returns relevant tools that can help accomplish tasks. Provider comparison: Inspect each candidate to confirm current scope/contracts; Probe each when current quotes are required. Call a sufficiently detailed result directly; inspection is optional. Results may include billing_rule metadata for rule-level pricing.
get_tools_by_ids tool_ids, search_id, session_id
[Deprecated: use "inspect" instead] Optionally inspect tools by ID when selection or valid request construction depends on missing/stale contract details. Provider comparison: Inspect each candidate to confirm current scope/contracts; Probe each when current quotes are required. Returns parameters, success rate, latency, examples, and billing_rule when available. For a public-to-authenticated continuation, retain the selected tool_id and omit the public search_id. Use the returned authenticated context for Call.
execute_tool sub_user_id, tool_id, search_id, params_to_tool, session_id, model, max_response_size, respond_with, require_zero_quote
[Deprecated: use "call" instead] Call a specific remote tool with provided parameters. Use a tool_id and current authenticated search_id from Discover or Inspect. A public search_id cannot be used for Call. Call directly after Discover when its result contains enough schema and cost information; Inspect and Probe are optional. Pass parameters to the tool through params_to_tool. Set require_zero_quote=true to require a current exact zero-credit quote before the server dispatches the Call. For uncertain outcomes, use the returned idempotency_key with lookup_execution; keys are issued by the host client and lookup never submits a new Call. Reuse only exact routes; rebuild current parameters and Call again for current/latest/today/time-sensitive data. The response may include pre-settlement billing; use usage_history or credits_ledger for final charge status.
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Install facts
| License | MIT |
|---|---|
| Needs | node >=18.2.0 |
| Source | github.com/QVerisAI/qveris-agent-toolkit |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-D+KhL1NKejK9Zcxem6ak72bo8oS6EqY99HbSqCMJnXSUGr+9mvUSEYawTnaLwTbcIIQ9m5PilWKJRqkCQcsPEQ== |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/%40qverisai/mcp)
New version out? Ask for a fresh report.