# io.github.QVerisAI/mcp (npm · @qverisai/mcp)

Discover, inspect and call ranked external data & tool APIs with unified billing and usage audit

- Trust score: 88/100 (high trust)
- Change this week: +9
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-11

## Components

- npm · `@qverisai/mcp`: 88/100 (this document), [markdown](https://verifymcp.io/servers/qverisai-mcp/qverisai-mcp.md), [page](https://verifymcp.io/servers/qverisai-mcp/qverisai-mcp)

## Channel facts

- Registry: `npm`
- Package: `@qverisai/mcp`
- Version: `0.14.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-11.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 96 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to QVerisAI/qveris-agent-toolkit).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 78/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1725 tokens (~172/item across 10 items; 9 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 53/100
  - Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add qverisai-mcp -- npx -y @qverisai/mcp
```

### Codex

```bash
codex mcp add qverisai-mcp -- npx -y @qverisai/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "qverisai-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@qverisai/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add qverisai-mcp --command npx --arg -y --arg @qverisai/mcp
```

### Hermes

```yaml
mcp_servers:
  qverisai-mcp:
    command: "npx"
    args: ["-y", "@qverisai/mcp"]
```

### Other

```json
{
  "mcpServers": {
    "qverisai-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@qverisai/mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-11 (score 88, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-08-10 (score 87, +2)

- [security improvement] GHSA-frvp-7c67-39w9 no longer affects this package
- [security improvement] Known CVEs: fail → pass
- [functional] Package version: 0.13.0 → 0.14.0

### 2026-08-09 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-08 (score 84, +4)

- [functional improvement] Security disclosure: fail → pass
- [functional] Dependency health: partial → 0.86

### 2026-08-06 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-04 (score 79, +35)

- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] Schema quality: unverified → good
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.30

### 2026-08-03 (score 44, 0)

- [functional] Package version: 0.12.0 → 0.13.0

### 2026-08-02 (score 44, +39)

- [security regression] GHSA-frvp-7c67-39w9 affects this package: medium
- [security regression] Known CVEs: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Provenance: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [security] The attested source repository moved: QVerisAI/qveris-agent-toolkit
- [functional regression] Security disclosure: fail → unverified
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional] Schema quality: Schema quality not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional] Tool coverage: Tool coverage not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet.
- [functional] Capabilities: Protocol version not yet verified: we do not have a sandbox capture of the MCP handshake this version of the package performs yet.
- [functional] Licence: MIT
- [functional] Package version: 0.12.0 → 0.13.0

## MCP tools (9)

### `discover` (~186 tokens)

Discover available tools based on natural language queries. Returns relevant tools that can help accomplish tasks. Use this to find tools before inspecting or calling them. Results may include billing_rule metadata for rule-level pricing.

Input parameters:

- `lang` (string): Response language. Omit to use server-side language negotiation.
- `limit` (number): Maximum number of results to return (1-100)
- `query` (string, required): The search query describing the general capability of the tool. Describe what you want to accomplish, not specific params you want to pass to the tool later. Example: "weather forecast API", "send em…
- `session_id` (string): Session identifier for tracking user sessions. If not provided, an auto-generated session ID will be used.
- `view` (string): Response projection. "routing" returns compact routing cards; "full" or omitted returns complete results.

Output parameters:

- `results` (array)
- `search_id` (string): Discovery id; thread into inspect/call.
- `total` (number)

### `inspect` (~124 tokens)

Inspect tools by their IDs to get detailed information. Returns parameters, success rate, latency, examples, and billing_rule when available. Use tool_ids from a previous discover call.

Input parameters:

- `search_id` (string): The search_id from the discover response that returned the tool(s). Optional but recommended for linking to the original discovery.
- `session_id` (string): Session identifier for tracking user sessions. If not provided, an auto-generated session ID will be used.
- `tool_ids` (array, required): Array of tool IDs to retrieve information for. These IDs should come from previous discover results.

Output parameters:

- `results` (array)
- `search_id` (string): Discovery id; thread into inspect/call.
- `total` (number)

### `probe` (~107 tokens)

Validate candidate parameters and obtain a zero-cost quote without executing the capability. Schema and quote are implemented; coverage and sample may return an explicit unknown verdict.

Input parameters:

- `checks` (array): Probe checks to request. Schema and quote are implemented; coverage and sample may be unknown.
- `live_budget` (string): Probe budget. Probe does not execute the capability or consume credits.
- `parameters` (object): Candidate parameters to validate.
- `tool_id` (string, required): Capability ID to validate without executing it.

Output parameters:

- `coverage` (object)
- `quote` (object)
- `sample` (object)
- `schema` (object)

### `call` (~282 tokens)

Call a specific remote tool with provided parameters. The tool_id and search_id must come from a previous discover call. Pass parameters to the tool through params_to_tool. The response may include pre-settlement billing; use usage_history or credits_ledger for final charge status.

Input parameters:

- `max_response_size` (number): Maximum size of response data in bytes. If tool generates data longer than this, it will be truncated and a download URL provided. Use -1 for no limit. Default is 20480 (20KB).
- `model` (string): Model that selected and parameterized this capability call.
- `params_to_tool` (object, required): A dictionary of parameters to pass to the remote tool. Keys are param names and values can be of any type. Example: {"city": "London", "units": "metric"}
- `respond_with` (string): Server-side result projection: "full", "summary", or "fields:<JSONPath,...>". Omit for full.
- `search_id` (string, required): The search_id from the discover response that returned this tool. Required for linking execution to the original discovery.
- `session_id` (string): Session identifier for tracking user sessions. If not provided, an auto-generated session ID will be used.
- `tool_id` (string, required): The ID of the remote tool to execute. Must come from a previous discover call.

Output parameters:

- `billing` (object)
- `execution_id` (string): Correlates with usage/ledger records.
- `remaining_credits` (number)
- `result`
- `success` (boolean)

### `usage_history` (~263 tokens)

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.

Input parameters:

- `bucket` (string): Aggregation bucket for summary mode.
- `charge_outcome` (string): Filter by charge outcome.
- `end_date` (string): End date in YYYY-MM-DD. Defaults to today UTC.
- `event_type` (string): Filter by event type, for example tool_execute or search.
- `execution_id` (string): Focus on one execution_id.
- `kind` (string): Backend usage kind grouping when supported.
- `limit` (number): Max rows for search mode. Default 10, hard max 50.
- `max_credits` (number): Maximum actual/requested credits to match.
- `min_credits` (number): Minimum actual/requested credits to match.
- `mode` (string): summary returns aggregates, search returns capped rows, export_file writes JSONL locally. Default: summary.
- `search_id` (string): Focus on one search_id.
- `start_date` (string): Start date in YYYY-MM-DD. Defaults to yesterday UTC.
- `success` (boolean): Filter by call success.

Output parameters:

- `items` (array)
- `matched_records` (number)
- `mode` (string)
- `shown_records` (number)

### `credits_ledger` (~217 tokens)

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.

Input parameters:

- `bucket` (string): Aggregation bucket for summary mode.
- `direction` (string): consume for negative ledger entries, grant for positive entries. Default: any.
- `end_date` (string): End date in YYYY-MM-DD. Defaults to today UTC.
- `entry_type` (string): Filter by ledger entry type, for example consume_tool_execute.
- `limit` (number): Max rows for search mode. Default 10, hard max 50.
- `max_credits` (number): Maximum absolute credit amount to match.
- `min_credits` (number): Minimum absolute credit amount to match.
- `mode` (string): summary returns aggregates, search returns capped rows, export_file writes JSONL locally. Default: summary.
- `start_date` (string): Start date in YYYY-MM-DD. Defaults to yesterday UTC.

Output parameters:

- `items` (array)
- `matched_records` (number)
- `mode` (string)
- `shown_records` (number)

### `search_tools` (~166 tokens)

[Deprecated: use "discover" instead] Search for available tools based on natural language queries.

Input parameters:

- `lang` (string): Response language. Omit to use server-side language negotiation.
- `limit` (number): Maximum number of results to return (1-100)
- `query` (string, required): The search query describing the general capability of the tool. Describe what you want to accomplish, not specific params you want to pass to the tool later. Example: "weather forecast API", "send em…
- `session_id` (string): Session identifier for tracking user sessions. If not provided, an auto-generated session ID will be used.
- `view` (string): Response projection. "routing" returns compact routing cards; "full" or omitted returns complete results.

Output parameters:

- `results` (array)
- `search_id` (string): Discovery id; thread into inspect/call.
- `total` (number)

### `get_tools_by_ids` (~111 tokens)

[Deprecated: use "inspect" instead] Get descriptions of tools based on their tool IDs.

Input parameters:

- `search_id` (string): The search_id from the discover response that returned the tool(s). Optional but recommended for linking to the original discovery.
- `session_id` (string): Session identifier for tracking user sessions. If not provided, an auto-generated session ID will be used.
- `tool_ids` (array, required): Array of tool IDs to retrieve information for. These IDs should come from previous discover results.

Output parameters:

- `results` (array)
- `search_id` (string): Discovery id; thread into inspect/call.
- `total` (number)

### `execute_tool` (~247 tokens)

[Deprecated: use "call" instead] Execute a specific remote tool with provided parameters.

Input parameters:

- `max_response_size` (number): Maximum size of response data in bytes. If tool generates data longer than this, it will be truncated and a download URL provided. Use -1 for no limit. Default is 20480 (20KB).
- `model` (string): Model that selected and parameterized this capability call.
- `params_to_tool` (object, required): A dictionary of parameters to pass to the remote tool. Keys are param names and values can be of any type. Example: {"city": "London", "units": "metric"}
- `respond_with` (string): Server-side result projection: "full", "summary", or "fields:<JSONPath,...>". Omit for full.
- `search_id` (string, required): The search_id from the discover response that returned this tool. Required for linking execution to the original discovery.
- `session_id` (string): Session identifier for tracking user sessions. If not provided, an auto-generated session ID will be used.
- `tool_id` (string, required): The ID of the remote tool to execute. Must come from a previous discover call.

Output parameters:

- `billing` (object)
- `execution_id` (string): Correlates with usage/ledger records.
- `remaining_credits` (number)
- `result`
- `success` (boolean)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/qverisai-mcp/qverisai-mcp#diagnostics

## Score history

- 2026-08-11: 88
- 2026-08-10: 87
- 2026-08-09: 85
- 2026-08-08: 84
- 2026-08-07: 80
- 2026-08-06: 80
- 2026-08-05: 79
- 2026-08-04: 79
- 2026-08-03: 44
- 2026-08-02: 44
- 2026-08-01: 5
- 2026-07-31: 28
- 2026-07-29: 6
- 2026-07-28: 51
- 2026-07-27: 51

## Links

- npm package: https://www.npmjs.com/package/@qverisai/mcp
- Socket report: https://socket.dev/npm/package/@qverisai/mcp
- Repository: https://github.com/QVerisAI/qveris-agent-toolkit
- Website: https://qveris.ai/
- Changelog RSS feed: https://verifymcp.io/servers/qverisai-mcp/qverisai-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/qverisai-mcp/qverisai-mcp.json
- HTML version of this page: https://verifymcp.io/servers/qverisai-mcp/qverisai-mcp