New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

QVeris Tool Discovery

by QVerisAI in QVerisAI/qveris-agent-toolkit

Finds, compares and calls third-party data and tool services through QVeris over MCP, and generates REST code for the ones worth keeping.

MITAuto-check passedAgent Workflows

Install QVeris Tool Discovery

skills CLI
$ npx skills add QVerisAI/qveris-agent-toolkit --skill qveris -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install QVerisAI/qveris-agent-toolkit qveris --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/QVerisAI/qveris-agent-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/qveris .claude/skills/qveris && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
qveris
GitHub stars
262
Token cost
~2.2k tokens
SKILL.md length
929 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Finds, compares and calls third-party data and tool services through QVeris over MCP, and generates REST code for the ones worth keeping.

  • Works in 2 steps: Find and Call Services via MCP → Generate Production Code
  • Needing a live data source or tool that the current environment lacks
  • SKILL.md covers When to use QVeris, Phase 1: Find and Call…, Billing and Audit and Phase 2: Generate Production…
  • Reaches qveris.ai; needs QVERIS_API_KEY and API_KEY

What it does

The agent decides between its connected tools and QVeris by task fit, data quality and freshness, cost, user constraints and call overhead. QVeris is the pick when the environment lacks a capability or live structured data source, when the right provider is not known, when providers should be compared on relevance, schema, quality, latency or cost, when a preferred provider fails and a fallback is needed, or when you ask for it. Local computation and ordinary reading of web pages do not need it.

Phase one runs over MCP. The agent calls `discover` with a description of the functionality wanted, not parameter names, asks for only a few results, and if the best one already shows parameter guidance and cost, calls it directly with `call`, passing arguments in `params_to_tool`. `inspect` is added only when contract details are missing or candidates need comparing, and `probe` only to validate parameters or get a current quote, which is not a price reservation or authorization. The shortest safe path, discover then call, is the default. The skill also covers generating production REST code for the services it finds.

When your agent uses it

  • Needing a live data source or tool that the current environment lacks
  • Comparing providers on cost, latency or data quality
  • Falling back to another provider when the preferred one fails
  • Generating REST code for a service found through QVeris

Example prompts

  • “Find a service that returns real-time exchange rates and call it for EUR to USD.”
  • “Compare two providers for company financial data and tell me which is cheaper.”
  • “The weather API failed; discover a fallback through QVeris and call it.”
  • “Use QVeris to find a geocoding service and generate the REST code to call it.”

Requirements

  • QVeris available through an MCP connection

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Find and Call Services via MCP
  2. Generate Production Code

What it can do on your machine

Read from SKILL.md and the folder at commit c7f1737. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • qveris.ai

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • QVERIS_API_KEY
    • API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

QVeris Tool Discovery loads about 2.2k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 929 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~74
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from QVerisAI/qveris-agent-toolkit at commit c7f1737, republished under its MIT licence (© QVerisAI). 929 words, ~2,217 tokens.

Download SKILL.mdSave it as .claude/skills/qveris/SKILL.md (or your agent's skills folder).
name
qveris
description
Access third-party professional data and tools through QVeris: find services, review supported scope when needed, call them, and generate production REST code. Use when existing tools are insufficient, a provider is unknown, comparison or fallback is needed, or the user requests QVeris.

For more detailed discovery query formulation, tool selection criteria, parameter handling, and error recovery, see the Agent Guidelines.

When to use QVeris

Choose among connected tools and QVeris using task fit, data quality/freshness, cost, user constraints, and call overhead. Use QVeris when at least one of these is true:

  • the current environment lacks the required capability or live/structured data source;
  • the correct provider or API is not known in advance;
  • the task benefits from comparing providers on relevance, schema, quality, latency, or cost;
  • the preferred provider is unavailable or fails and a fallback is needed;
  • the user explicitly asks to discover or call a capability through QVeris.

Local computation and transformations do not need QVeris. For qualitative pages, tutorials, or factual browsing, use an available browsing tool unless structured API data or provider routing is required.

When external functionality is needed, follow this two-phase workflow. Discover, Inspect, Probe, and Call are independent protocol actions, not four mandatory steps.

Phase 1: Find and Call Services via MCP

  1. Identify the service or data/tool access the user needs.
  2. Call discover with a functionality description (not parameter names). Request only a few results unless comparison is necessary.
  3. If the best discovery result already includes enough parameter guidance and cost information, call it directly with call, passing parameters via params_to_tool.
  4. Use inspect only when selection or valid request construction depends on contract details omitted by Discover, multiple candidates need comparison, or a host-managed metadata entry needs refreshing.
  5. Use probe only when parameters need validation, a current quote is needed for a budget decision, or the user explicitly wants a preflight. Probe is not a prerequisite for Call; its quote is not a price reservation or user authorization.
  6. Repeat or broaden the discovery query only if no suitable capability is found or a safe fallback is needed.

Optimize for the shortest safe path:

  • Default: discover → call.
  • Known current capability with valid discovery provenance and a current contract: call directly if the active integration supports that reuse.
  • Add inspect and/or probe only when their information changes the selection or prevents a material error.
  • Do not call a read-only step merely to complete a ritual sequence.
Context reuse

Do not assume generic MCP or stateless SDK clients provide semantic route memory. Preserve the selected result's real search_id within the active flow. If the host explicitly exposes a current known-capability entry, reuse it only for an exact capability intent and unchanged provider/coverage constraints; rebuild all business parameters from the current request.

Inspect when that host entry's contract is missing or stale. Discover again when intent, coverage, provider, authorization, or endpoint context changes; the entry expires; the capability is unavailable; or comparison/fallback is needed. Never invent search_id, reuse another discovery's attribution, or cache credentials, sensitive user values, or business results.

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.

An explicit empty parameter contract means the tool takes no parameters. A missing contract is not equivalent: Inspect it or request the missing business input before Call. Preserve required, enum, and alternative/one-of constraints. Never copy sample values as if they were the user's request.

Compatibility note: legacy MCP names search_tools, get_tools_by_ids, and execute_tool remain deprecated aliases only. Prefer discover, inspect, and call in all new workflows.

Show full SKILL.md (335 more words)Show less

Billing and Audit

QVeris separates pricing rules, pre-settlement billing, and final settlement:

  • billing_rule explains how a capability is priced.
  • billing / pre_settlement_bill explains the theoretical charge for a call.
  • usage_history and credits_ledger answer whether credits were actually charged and how the balance changed.

When the user asks whether a failed call was charged, do not infer from cost alone. Query usage_history with the execution_id and inspect charge_outcome.

Use context-safe audit patterns:

  • Start with mode: "summary" for usage or ledger totals.
  • Use mode: "search" with precise filters such as execution_id, charge_outcome, min_credits, max_credits, or a date range.
  • Use mode: "export_file" for large analysis; read the resulting JSONL file in chunks instead of returning all rows into context.

Phase 2: Generate Production Code

Once a suitable tool is identified, generate code that calls the QVeris REST API directly. Do not reuse the MCP tool-call result — produce standalone code the user can run.

  • Read the API key from the caller's QVERIS_API_KEY environment variable; do not retrieve or expose MCP configuration secrets
  • Use a timeout appropriate to the selected capability (60 seconds by default); never automatically repeat a paid Call after a timeout or unknown execution outcome
  • Handle errors by checking the success field and error_message
  • Verify the response structure matches expectations before delivering to the user; if the call fails (invalid key, rate limit, tool not found), report the error and suggest corrective action
Example: Fetch Weather Data
python
import requests

import os

API_KEY = os.environ.get("QVERIS_API_KEY")
BASE_URL = os.environ.get("QVERIS_BASE_URL", "https://qveris.ai/api/v1").rstrip("/")

if not API_KEY:
    raise RuntimeError("Set QVERIS_API_KEY before running this code")

def call_tool(tool_id: str, search_id: str, params: dict) -> dict:
    """Call a QVeris capability and return the result."""
    resp = requests.post(
        f"{BASE_URL}/tools/execute",
        params={"tool_id": tool_id},
        headers={"Authorization": f"Bearer {API_KEY}"},
        json={
            "search_id": search_id,
            "session_id": "",
            "parameters": params,
            "max_response_size": 20480,
        },
        timeout=60,
    )
    resp.raise_for_status()
    try:
        data = resp.json()
    except requests.exceptions.JSONDecodeError:
        raise RuntimeError("Failed to decode API response as JSON.")

    if not data.get("success"):
        raise RuntimeError(f"QVeris error: {data.get('error_message', 'Unknown error')}")

    result = data.get("result")
    if result is None:
        raise RuntimeError("API response is missing the 'result' field.")
    return result

# Usage
result = call_tool(
    tool_id="<tool_id selected in Phase 1>",
    search_id="<search_id from Phase 1>",
    params={"city": "London", "units": "metric"},
)
print(result)  # {"data": {"temperature": 15.5, "humidity": 72}}
API Reference

Base URL: https://qveris.ai/api/v1 by default. Set QVERIS_BASE_URL to the active deployment's API root when an explicit override is required.

Authentication: Authorization: Bearer YOUR_API_KEY

POST /tools/execute?tool_id={tool_id}

FieldTypeDescription
search_idstringID returned by discover
session_idstringOptional session identifier
parametersobjectTool-specific input parameters
max_response_sizenumberMax response bytes (default 20480)

Response Fields

FieldTypeDescription
execution_idstringUnique ID for the execution.
resultobjectContains the tool's output, typically under a data key.
successbooleantrue if the call succeeded, false otherwise.
error_messagestringDetails of the error if success is false.
elapsed_time_msnumberExecution time in milliseconds.

© QVerisAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/qveris of QVerisAI/qveris-agent-toolkit.

Open the folder on GitHubat commit c7f1737

Compare with similar skills

QVeris Tool Discovery next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

QVeris Tool Discovery compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
QVeris Tool Discovery this skillQVerisAI/qveris-agent-toolkit262—~2.2kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
Build MCP Serveranthropics/claude-plugins-official38k1 repos~3kAutomated safety check: PassApache-2.0
LexGuard MCP Developer GuideSeoNaRu/lexguard-mcp131—~1.1kAutomated safety check: PassCustom licence
MCP API Key AuthenticationYourdaylight/stock_datasource189—~1.2kAutomated safety check: PassMIT

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • Build MCP Server

    anthropics/claude-plugins-official

    Official

    Entry point for building an MCP server: asks about the use case, picks a deployment model and tool-design pattern, then hands off to more specialized skills.

    38k GitHub starsUsed in 1 repo~3k tokens
    Agent WorkflowsAuto-check passed

  • LexGuard MCP Developer Guide

    SeoNaRu/lexguard-mcp

    Developer guide for the LexGuard Korean law MCP server: layer rules, adding tools and repositories, JSON-RPC responses, law API handling, answer rules and tests.

    131 GitHub stars~1.1k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

  • MCP API Key Authentication

    Yourdaylight/stock_datasource

    Sets up and troubleshoots MCP API key authentication for a stock data service, covering key creation, client configuration and per-tool usage statistics.

    189 GitHub stars~1.2k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed

  • Atlassian MCP Expert

    Jeffallan/claude-skills

    Queries and edits Jira issues and Confluence pages through an MCP server, covering JQL and CQL queries, server setup, authentication and sprint or backlog workflows.

    12k GitHub stars~1.3k tokensUpdated 7 days ago
    Backend & APIsAuto-check passed

More from QVerisAI/qveris-agent-toolkit

  • QVeris CLI

    QVerisAI/qveris-agent-toolkit

    Finds third-party data and tool providers through the QVeris CLI, inspects their contracts and calls them, with usage tracking, when the agent's own tools fall short.

    262 GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed

Works with

Categories

Questions about QVeris Tool Discovery

What does QVeris Tool Discovery do?

Finds, compares and calls third-party data and tool services through QVeris over MCP, and generates REST code for the ones worth keeping. The agent decides between its connected tools and QVeris by task fit, data quality and freshness, cost, user constraints and call overhead. QVeris is the pick when the environment lacks a capability or live structured data source, when the right provider is not known, when providers should be compared on relevance, schema, quality, latency or cost, when a preferred provider fails and a fallback is needed, or when you ask for it.

When should I use QVeris Tool Discovery?

QVeris Tool Discovery fits situations like: needing a live data source or tool that the current environment lacks; comparing providers on cost, latency or data quality; falling back to another provider when the preferred one fails; generating REST code for a service found through QVeris.

How do I install QVeris Tool Discovery in Claude Code?

Run `npx skills add QVerisAI/qveris-agent-toolkit --skill qveris -a claude-code`. Or copy the skill folder (skills/qveris in QVerisAI/qveris-agent-toolkit) into .claude/skills/qveris in your project. Claude Code loads it when a task matches its description.

How do I install QVeris Tool Discovery in Codex?

Run `npx skills add QVerisAI/qveris-agent-toolkit --skill qveris -a codex`. Or copy the skill folder (skills/qveris in QVerisAI/qveris-agent-toolkit) into .agents/skills/qveris in your project. Codex loads it when a task matches its description.

Can I use QVeris Tool Discovery in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add QVerisAI/qveris-agent-toolkit --skill qveris -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/qveris, .gemini/skills/qveris, .github/skills/qveris and .opencode/skills/qveris in your project.

What does QVeris Tool Discovery need to run?

Going by SKILL.md and its folder, QVeris Tool Discovery needs credentials named QVERIS_API_KEY and API_KEY. Our summary lists: QVeris available through an MCP connection.

Does QVeris Tool Discovery access the network?

SKILL.md names 1 domain. In commands or code: qveris.ai; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is QVeris Tool Discovery safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does QVeris Tool Discovery use?

QVeris Tool Discovery is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does QVeris Tool Discovery use?

About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to QVeris Tool Discovery?

Skills that share tags, products or a category with QVeris Tool Discovery: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), Build MCP Server (anthropics/claude-plugins-official, 38k stars) and LexGuard MCP Developer Guide (SeoNaRu/lexguard-mcp, 131 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains QVeris Tool Discovery?

QVerisAI (a GitHub organization) maintains it in QVerisAI/qveris-agent-toolkit, which has 262 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 9, 2026.

Source: QVerisAI/qveris-agent-toolkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.