Skip to content
Back to search

qveris-agent-toolkit

Bring professional data and tools to the AI you already use: open-source MCP, CLI, SDKs, skills, and docs to find services, call them, and audit usage.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/QVerisAI/qveris-agent-toolkit with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/QVerisAI/qveris-agent-toolkit'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/qverisai--qveris-agent-toolkit/badge.svg)](/listings/qverisai--qveris-agent-toolkit)

HTML

<a href="/listings/qverisai--qveris-agent-toolkit"><img src="/api/listings/qverisai--qveris-agent-toolkit/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These steps run a script from the network that findsafeskills does not scan.

๐Ÿค– I'm an Agent

> Your owner sent you here to learn about QVeris? > โ†’ If you are an OpenClaw-style skill agent, use the official skill: [skills/openclaw/qveris-official/SKILL.md](skills/openclaw/qveris-official/SKILL.md) > โ†’ If you are running in Cursor / Claude Code / OpenCode, follow the [Agent capability guide & install protocol](agent/SETUP.md) > โ†’ Default path: Discover (free) โ†’ Call; use Inspect or Probe only when additional verification is needed

๐Ÿง‘โ€๐Ÿ’ป I have OpenClaw / Cursor / Claude Code installed

> Copy this to your Agent โ€” done in 30 seconds: > `Install QVeris skill following https://qveris.ai/skill/instruct.md and use QVERIS_API_KEY=your-key` > โ†’ [Get API Key](https://qveris.ai/account?page=api-keys) (free, 1,000 one-time trial credits after signup verification)

โš™๏ธ I'm a developer integrating via CLI / MCP / API / SDK

> โ†’ **[QVeris CLI](packages/cli)** โ€” `npm install -g @qverisai/cli` or `curl -fsSL https://qveris.ai/cli/install | bash` > โ†’ [MCP Server Doc](docs/en-US/mcp-server.md) > โ†’ [REST API Doc](docs/en-US/rest-api.md) > โ†’ [Python SDK](packages/python-sdk)

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md ยท README ยท 367 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <div align="center">
  2. <img src="assets/logo-light.png" width="120" alt="QVeris Logo" />
  3. <h1>QVeris Agent Toolkit</h1>
  4. <p><strong>Bring professional data to the AI you already use.</strong></p>
  5. <p>QVeris is a professional data and tool access platform for AI. This open-source toolkit provides the CLI, MCP server, Python SDK, skills, and REST API docs that help AI assistants, products, and workflows find services, review supported scope, call them, and audit usage.</p>
  6. <p>
  7. Website: <a href="https://qveris.ai" target="_blank"><b>https://qveris.ai</b></a>
  8. </p>
  9. <p>
  10. <b>๐Ÿ‡บ๐Ÿ‡ธ English</b> ยท
  11. <a href="README_zh-CN.md">๐Ÿ‡จ๐Ÿ‡ณ ็ฎ€ไฝ“ไธญๆ–‡</a>
  12. </p>
  13. <p>
  14. <a href="https://github.com/QVerisAI/qveris-agent-toolkit">
  15. <img src="https://img.shields.io/github/stars/QVerisAI/qveris-agent-toolkit?style=social" alt="GitHub stars" />
  16. </a>
  17. <a href="https://github.com/QVerisAI/qveris-agent-toolkit/actions/workflows/contract-tests.yml">
  18. <img src="https://github.com/QVerisAI/qveris-agent-toolkit/actions/workflows/contract-tests.yml/badge.svg?branch=main" alt="CI" />
  19. </a>
  20. <a href="https://www.npmjs.com/package/@qverisai/cli">
  21. <img src="https://img.shields.io/npm/v/@qverisai/cli?label=cli" alt="cli npm version" />
  22. </a>
  23. <a href="https://www.npmjs.com/package/@qverisai/mcp">
  24. <img src="https://img.shields.io/npm/v/@qverisai/mcp?label=mcp" alt="mcp npm version" />
  25. </a>
  26. <a href="https://www.npmjs.com/package/@qverisai/sdk">
  27. <img src="https://img.shields.io/npm/v/@qverisai/sdk?label=js-sdk" alt="js-sdk npm version" />
  28. </a>
  29. <a href="https://pypi.org/project/qveris/">
  30. <img src="https://img.shields.io/pypi/v/qveris?label=python-sdk" alt="PyPI version" />
  31. </a>
  32. <a href="https://github.com/QVerisAI/qveris-agent-toolkit/blob/main/LICENSE">
  33. <img src="https://img.shields.io/github/license/QVerisAI/qveris-agent-toolkit" alt="license" />
  34. </a>
  35. </p>
  36. </div>
  37. ---
  38. - Professional data and tools across finance, search, weather, maps, documents, and more
  39. - `Discover / Call` is the default path; `Inspect` and `Probe` are conditional checks for missing/stale contracts, comparison, parameter validation, or a current quote
  40. - For provider comparison, Inspect every candidate when current scope or a complete contract must be confirmed; a Discover summary is not confirmation. Probe every candidate when the comparison requires a current quote. Reuse may preserve an exact route, never business parameters or results: build parameters from the current request, and make a fresh Call for current, latest, today, or other time-sensitive data.
  41. - `Discover` is free. `Call` returns structured pre-settlement billing, with final charge outcomes available through usage audit and credits ledger views.
  42. - **NEW** `QVeris CLI` โ€” command-line access to professional data and tools for agents. [Learn more](#qveris-cli)
  43. - Works with `CLI` / `MCP` / `Python SDK` / `REST API`
  44. **When to use QVeris:** use it when built-in tools are insufficient, a provider must be found dynamically, comparison or fallback matters, or the user requests it. Keep using local or native tools when they already fit the task.
  45. ---
  46. ## No account or API key yet?
  47. [Try a supported tool in your browser](https://qveris.ai/discover?trial=1): explicitly activate the trial, review its actual allowance and expiry, and confirm each quote. Save it to an account later. For terminal use, run `qveris auth trial` explicitly; see the [CLI trial guide](docs/en-US/cli.md#explicit-anonymous-trial) for secure credentials and the separate Agent trial policy. For a first result with no account, use `qveris discover "weather forecast API" --public-read-only --limit 1 --json` in a credential-free profile. Public discovery creates no trial or paid execution. For authenticated access, prefer browser OAuth where supported; keep an existing API key private. See [repository Agent guidance](AGENTS.md).
  48. ## Quick Start
  49. ### ๐Ÿค– I'm an Agent
  50. > Your owner sent you here to learn about QVeris?
  51. > โ†’ If you are an OpenClaw-style skill agent, use the official skill: [skills/openclaw/qveris-official/SKILL.md](skills/openclaw/qveris-official/SKILL.md)
  52. > โ†’ If you are running in Cursor / Claude Code / OpenCode, follow the [Agent capability guide & install protocol](agent/SETUP.md)
  53. > โ†’ Default path: Discover (free) โ†’ Call; use Inspect or Probe only when additional verification is needed
  54. ### ๐Ÿง‘โ€๐Ÿ’ป I have OpenClaw / Cursor / Claude Code installed
  55. > Copy this to your Agent โ€” done in 30 seconds:
  56. > `Install QVeris skill following https://qveris.ai/skill/instruct.md. Do not request or include credentials in this chat.`
  57. > โ†’ [Get API Key](https://qveris.ai/account?page=api-keys) (free, 1,000 one-time trial credits after signup verification)
  58. Configure `QVERIS_API_KEY` privately in your clientโ€™s secret store or local environment, or complete browser OAuth when supported. Never include the key in installation prompts or chat.
  59. ### โš™๏ธ I'm a developer integrating via CLI / MCP / API / SDK
  60. > โ†’ **[QVeris CLI](packages/cli)** โ€” `npm install -g @qverisai/cli` or `curl -fsSL https://qveris.ai/cli/install | bash`
  61. > โ†’ [MCP Server Doc](docs/en-US/mcp-server.md)
  62. > โ†’ [REST API Doc](docs/en-US/rest-api.md)
  63. > โ†’ [Python SDK](packages/python-sdk)
  64. ---
  65. ## For Agents
  66. If you are an AI Agent evaluating whether to use QVeris, here is what you need to know.
  67. **What QVeris gives you:**
  68. - `Discover` โ€” find candidate services with natural language (free)
  69. - `Inspect` โ€” optionally check missing or stale parameters, available signals, and billing details
  70. - `Call` โ€” invoke a selected service and receive structured results and pre-settlement billing when available
  71. - `Usage audit` / `Credits ledger` โ€” review request and credit outcomes through the interfaces that expose them
  72. - **QVeris CLI** โ€” access services via `qveris discover/inspect/call` without preloading the full service catalog
  73. - Professional data and tools across finance, search, weather, maps, documents, social, blockchain, healthcare, and more
  74. - Per-tool execution history, success-rate, and latency signals when supplied
  75. **How to install:**
  76. - **CLI (recommended)**: `curl -fsSL https://qveris.ai/cli/install | bash` โ€” then use `qveris discover/inspect/call`
  77. - See [SETUP.md](agent/SETUP.md) โ€” supports OpenClaw / Claude Code / Cursor / OpenCode / Trae
  78. - Install does not modify shell startup files by default (session-scoped)
  79. - Must pass file checks + CLI verification to confirm success
  80. **How to explain to your owner:**
  81. > QVeris helps me find a service when the tools I already have are insufficient, review its supported scope when needed, and call it. Installation does not change system configuration unless explicitly requested. Call pricing and usage or credit records depend on the selected capability and supported interface.
  82. **Billing and audit:**
  83. - Discover: **free**
  84. - Call: priced by structured `billing_rule`; call responses may include compact pre-settlement `billing`
  85. - Final charge status: check `qveris usage` / `usage_history`
  86. - Final balance movement: check `qveris ledger` / `credits_ledger`
  87. - Free tier: 1,000 one-time trial credits after signup verification
  88. - $19 = 10,000 credits (pay-as-you-go, credits never expire)
  89. - Details: [qveris.ai/pricing](https://qveris.ai/pricing)
  90. ---
  91. ## 30-Second Setup
  92. 1. [Get API Key](https://qveris.ai/account?page=api-keys) (free, 1,000 one-time trial credits after signup verification)
  93. ### OpenClaw users
  94. Send this to your Agent:
  95. ```
  96. Install QVeris skill following https://qveris.ai/skill/instruct.md. Do not request or include credentials in this chat.
  97. ```
  98. The Agent will download the [official OpenClaw skill](skills/openclaw/qveris-official/SKILL.md) and complete installation automatically.
  99. ### Cursor / Claude Code / OpenCode users
  100. Follow the [setup guide (agent/SETUP.md)](agent/SETUP.md) โ€” your Agent will configure MCP server + [skill](skills/qveris/SKILL.md) for your environment.
  101. #### Cursor Marketplace plugin
  102. The Cursor plugin in this repository bundles the hosted QVeris MCP connection and the official QVeris skills. After installing it from Cursor Marketplace:
  103. 1. Open the plugin configuration and enter your `QVERIS_API_KEY`.
  104. 2. Start a new agent session so Cursor can connect to `https://mcp.qveris.ai/mcp`.
  105. 3. Confirm that `discover`, `inspect`, `probe`, `call`, `usage_history`, and `credits_ledger` are available.
  106. The API key is stored by Cursor as a plugin variable and is never committed to this repository.
  107. #### Gemini CLI extension
  108. Install QVeris directly from this repository:
  109. ```bash
  110. gemini extensions install https://github.com/QVerisAI/qveris-agent-toolkit
  111. ```
  112. During installation, enter your `QVERIS_API_KEY` when prompted. Gemini CLI stores it as a sensitive extension setting and connects to the hosted QVeris MCP server at `https://mcp.qveris.ai/mcp`.
  113. Restart Gemini CLI after installation, then run `/mcp` to confirm that the `qveris` server is connected and its tools are available.
  114. ### After setup
  115. Try a task: "Check the current weather in Tokyo"
  116. **Safety:**
  117. - Install does not modify your shell config (unless you explicitly ask)
  118. - Capability calls are remote API requests and do not grant a called service access to your local filesystem or system configuration
  119. - You can review usage and credit records through supported interfaces
  120. ---
  121. ## QVeris CLI
  122. **Access professional data and tools from your agent's shell.**
  123. CLI executes as a subprocess and finds services on demand, without preloading the full service catalog. Instructions, commands, and results still consume context tokens. QVeris MCP likewise exposes a compact tool surface instead of every service definition.
  124. ```bash
  125. # Install (one-liner)
  126. curl -fsSL https://qveris.ai/cli/install | bash
  127. # Or via npm
  128. npm install -g @qverisai/cli
  129. ```
  130. ```bash
  131. # Guided first call: `init` handles selection and validation for you
  132. $ qveris init
  133. # Default agent workflow: discover โ†’ call
  134. $ qveris discover "weather forecast API"
  135. Found 5 capabilities matching your query
  136. 1. gridpoint_forecast by Weather.gov
  137. params: wfo (string, required), x (number, required), y (number, required)
  138. $ qveris call 1 --params '{"wfo":"LWX","x":90,"y":90}'
  139. โœ“ success
  140. { "forecast": "Sunny, high near 75..." }
  141. # Optional when selection or request construction needs missing details
  142. $ qveris inspect 1
  143. # Optional when parameters need validation or a budget decision needs a current quote
  144. $ qveris probe 1 --params '{"wfo":"LWX","x":90,"y":90}' --checks schema,quote
  145. $ qveris usage --mode search --execution-id <execution_id>
  146. # Confirms charge_outcome and actual_amount_credits for that call
  147. ```
  148. ### Why CLI over MCP for agents?
  149. | | CLI | MCP |
  150. |---|---|---|
  151. | **Token cost** | No upfront catalog schemas; command/result tokens still apply | Depends on client context handling and exposed routing schemas |
  152. | **Startup** | Instant (`npx` or global install) | Requires server process + transport handshake |
  153. | **Output** | Deterministic schema, `--json` for parsing | JSON over stdio, varies by client |
  154. | **Scalability** | On-demand discovery, no catalog preloading | Routing schemas stay separate from catalog size |
  155. | **Debugging** | Visible in terminal, `--dry-run` preview | Opaque, buried in MCP logs |
  156. | **Auth** | Built-in endpoint; explicit override via `QVERIS_BASE_URL` | Same |
  157. Usage and ledger commands default to aggregated summaries. Large audit exports are written to local JSONL files under `.qveris/exports/` instead of being printed into Agent context.
  158. **When to use CLI**: Agent frameworks that support `exec` / `bash` tool (Claude Code, OpenClaw, Cursor terminal, etc.)
  159. **When to use MCP**: IDE integrations that only support MCP protocol (Cursor inline, Claude Desktop)
  160. Full CLI documentation: [packages/cli/README.md](packages/cli/README.md)
  161. ---
  162. ## Developer Integration
  163. ### Access methods
  164. | Method | Use case | Docs |
  165. |--------|----------|------|
  166. | **CLI** (recommended) | Claude Code / OpenClaw / any agent with exec | [CLI docs](packages/cli/README.md) |
  167. | MCP Server | Cursor / Claude Desktop / MCP-only clients | [MCP docs](docs/en-US/mcp-server.md) |
  168. | Python SDK | Python projects, agent frameworks | [Python SDK docs](packages/python-sdk/README.md) |
  169. | TypeScript SDK | Node.js / TypeScript projects | [JS SDK docs](packages/js-sdk/README.md) |
  170. | REST API | Any language, custom integrations | [REST API docs](docs/en-US/rest-api.md) |
  171. Stuck? See [Troubleshooting & FAQ](docs/troubleshooting.md).
  172. ### Service access workflow
  173. Agents use three service-access actions, plus two read-only record paths:
  174. | Action | API endpoint | Description |
  175. |--------|-------------|-------------|
  176. | **Discover** | `POST /search` | Find capabilities with natural language, returns candidates |
  177. | **Inspect** | `POST /tools/by-ids` | View capability details, parameters, quality signals |
  178. | **Call** | `POST /tools/execute` | Invoke a capability, get structured results, and optionally record model attribution |
  179. | **Usage audit** | `GET /auth/usage/history/v2` | Check request status, charge outcome, and actual charge |
  180. | **Credits ledger** | `GET /auth/credits/ledger` | Check final credit balance movements |
  181. The reproducible [Discover โ†’ Call accuracy benchmark](docs/en-US/discover-call-benchmark.md)
  182. measures grounded selection, parameterization, and real execution success per
  183. model. Its task set, runner, raw-record format, and deterministic scorer are
  184. public under [`benchmarks/discover-call`](benchmarks/discover-call/README.md).
  185. ### Professional data and tool access
  186. - A service catalog across multiple professional-data and tool categories
  187. - Parameter schemas, examples, success rate, and average latency are available when supplied for a service
  188. - Supports `private` / `org` / `public` service visibility levels
  189. - Browse available services: [qveris.ai/providers](https://qveris.ai/providers)
  190. ---
  191. ## Pricing
  192. QVeris uses pay-as-you-go pricing. No subscriptions.
  193. | Plan | Price | Credits | Notes |
  194. |------|-------|---------|-------|
  195. | Free | $0 | 1,000 trial credits | One-time grant after signup verification |
  196. | Standard | $19 | 10,000 credits | Buy on demand, never expire |
  197. | Scale | See pricing page | Based on selected package | Current packages and bonuses shown at checkout |
  198. - **Discover is free** โ€” Agents can explore all capabilities at zero cost
  199. - **Call** is priced by structured billing rules, with final charges auditable through usage history and the credits ledger
  200. - No monthly fees, no auto-renewal
  201. - Details: [qveris.ai/pricing](https://qveris.ai/pricing)
  202. ---
  203. ## Security & Trust
  204. - Capability calls are remote API requests and do not grant a called service access to your local filesystem or system configuration
  205. - Session-scoped config, no system file modifications by default
  206. - Usage and credit records through supported interfaces
  207. - RBAC and per-capability access control
  208. - Rate limiting and quota enforcement
  209. - Enterprise options (VPC / private cloud) planned
  210. ---
  211. ## What's New
  212. Latest capabilities and updates: [qveris.ai](https://qveris.ai)
  213. ---
  214. ## Open Ecosystem
  215. QVeris provides managed service access alongside open-source client tooling. We actively support the ecosystem by open-sourcing the MCP server, SDKs, Agent skills, and plugins, and by contributing code upstream.
  216. ### Monorepo packages
  217. This repository (`QVerisAI/qveris-agent-toolkit`) is the primary monorepo for QVeris client-side tooling:
  218. | Package | Path | Distribution |
  219. |---------|------|--------------|
  220. | MCP Server | [`packages/mcp`](packages/mcp) | [@qverisai/mcp](https://www.npmjs.com/package/@qverisai/mcp) |
  221. | CLI | [`packages/cli`](packages/cli) | [@qverisai/cli](https://www.npmjs.com/package/@qverisai/cli) |
  222. | Python SDK | [`packages/python-sdk`](packages/python-sdk) | [qveris](https://pypi.org/project/qveris/) |
  223. | TypeScript SDK | [`packages/js-sdk`](packages/js-sdk) | [@qverisai/sdk](https://www.npmjs.com/package/@qverisai/sdk) |
  224. | Agent docs | [`agent/`](agent) | โ€” |
  225. | Skills | [`skills/`](skills) | โ€” |
  226. ### Recipes and ecosystem manifests
  227. Use [`recipes/`](recipes) for copy-paste workflow templates across finance research, risk/compliance, crypto monitoring, data analysis, and developer automation. The flagship recipes ship a runnable `run.sh`, and each package has runnable examples: [js-sdk](packages/js-sdk/examples), [MCP](packages/mcp/examples), [CLI](packages/cli/examples), and [Python SDK](packages/python-sdk/examples).
  228. Use [`ecosystem/`](ecosystem) for the versioned QVeris manifest schema, marketplace-ready listing fields, permission declarations, contribution guide, and compatibility matrix.
  229. ### Other repositories
  230. | Repository | Description |
  231. |------------|-------------|
  232. | [QVerisAI/open-qveris-skills](https://github.com/QVerisAI/open-qveris-skills) | Community skills (stock copilot, market reports, etc.) |
  233. | [QVerisAI/openclaw-qveris-plugin](https://github.com/QVerisAI/openclaw-qveris-plugin) | OpenClaw plugin |
  234. | [QVerisAI/vscode-qveris-ai](https://github.com/QVerisAI/vscode-qveris-ai) | VS Code extension |
  235. Full list: [github.com/orgs/QVerisAI/repositories](https://github.com/orgs/QVerisAI/repositories)
  236. ### Distribution channels
  237. - **npm**: [@qverisai](https://www.npmjs.com/org/qverisai) โ€” MCP server, CLI
  238. - **PyPI**: [qveris](https://pypi.org/project/qveris/) โ€” Python SDK
  239. - **ClawHub**: [clawhub.ai/skills?q=qveris](https://clawhub.ai/skills?sort=downloads&q=qveris) โ€” OpenClaw skills
  240. - **One-liner install**: `curl -fsSL https://qveris.ai/cli/install | bash`
  241. ### Upstream contributions
  242. QVeris actively contributes to the broader Agent ecosystem:
  243. - [openclaw/openclaw](https://github.com/openclaw/openclaw) โ€” OpenClaw runtime
  244. - [openclaw/clawhub](https://github.com/openclaw/clawhub) โ€” ClawHub skill registry
  245. ---
  246. ## Community
  247. - ๐Ÿฆ **X (Twitter)**: [x.com/QVerisAI](https://x.com/QVerisAI)
  248. - ๐Ÿ’ผ **LinkedIn**: [linkedin.com/company/qveris](https://www.linkedin.com/company/qveris)
  249. - ๐Ÿ“š **Docs**: [qveris.ai/docs](https://qveris.ai/docs)
  250. - ๐Ÿงช **Playground**: [qveris.ai/playground](https://qveris.ai/playground)
  251. ---
  252. ## โญ Star & Share
  253. If you are building AI products or workflows that need professional data and tools, **star this repo** and share it with other builders.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If itโ€™s helped, pass it on.