MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
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.
Install QVeris CLI
$ npx skills add QVerisAI/qveris-agent-toolkit --skill qveris-cli -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install QVerisAI/qveris-agent-toolkit qveris-cli --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/QVerisAI/qveris-agent-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/qveris-cli .claude/skills/qveris-cli && rm -rf skills-srcUse ~/.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/
Install the "qveris-cli" agent skill from https://github.com/QVerisAI/qveris-agent-toolkit/tree/main/skills/qveris-cli into .claude/skills/qveris-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qveris-cli", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/QVerisAI/qveris-agent-toolkit/tree/main/skills/qveris-cliType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add QVerisAI/qveris-agent-toolkit --skill qveris-cli -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install QVerisAI/qveris-agent-toolkit qveris-cli --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/QVerisAI/qveris-agent-toolkit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/qveris-cli .agents/skills/qveris-cli && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "qveris-cli" agent skill from https://github.com/QVerisAI/qveris-agent-toolkit/tree/main/skills/qveris-cli into .agents/skills/qveris-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qveris-cli", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add QVerisAI/qveris-agent-toolkit --skill qveris-cli -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install QVerisAI/qveris-agent-toolkit qveris-cli --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/QVerisAI/qveris-agent-toolkit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/qveris-cli .cursor/skills/qveris-cli && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "qveris-cli" agent skill from https://github.com/QVerisAI/qveris-agent-toolkit/tree/main/skills/qveris-cli into .cursor/skills/qveris-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qveris-cli", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/QVerisAI/qveris-agent-toolkit.git --path skills/qveris-cli--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add QVerisAI/qveris-agent-toolkit --skill qveris-cli -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install QVerisAI/qveris-agent-toolkit qveris-cli --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/QVerisAI/qveris-agent-toolkit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/qveris-cli .gemini/skills/qveris-cli && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "qveris-cli" agent skill from https://github.com/QVerisAI/qveris-agent-toolkit/tree/main/skills/qveris-cli into .gemini/skills/qveris-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qveris-cli", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install QVerisAI/qveris-agent-toolkit qveris-cliInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add QVerisAI/qveris-agent-toolkit --skill qveris-cli -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/QVerisAI/qveris-agent-toolkit.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/qveris-cli .github/skills/qveris-cli && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "qveris-cli" agent skill from https://github.com/QVerisAI/qveris-agent-toolkit/tree/main/skills/qveris-cli into .github/skills/qveris-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qveris-cli", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add QVerisAI/qveris-agent-toolkit --skill qveris-cli -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install QVerisAI/qveris-agent-toolkit qveris-cli --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/QVerisAI/qveris-agent-toolkit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/qveris-cli .opencode/skills/qveris-cli && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "qveris-cli" agent skill from https://github.com/QVerisAI/qveris-agent-toolkit/tree/main/skills/qveris-cli into .opencode/skills/qveris-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qveris-cli", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
qveris-cli- GitHub stars
- 261
- Token cost
- ~1.1k tokens
- SKILL.md length
- 436 words
- Files
- 2
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- MIT
At a glance
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.
- Works in 3 steps: For a definite validation failure, fix… → Drop optional parameters only if doing… → Switch to another compatible result only…
- Finding an external data API the agent has no tool for
- SKILL.md covers Quick first run, Commands, Response Size and Session Mechanism, plus 3 more sections
- Calls npx; needs QVERIS_API_KEY
What it does
The skill covers the discover, inspect and call loop of the QVeris CLI. A first-run init wizard handles authentication, discovery, inspection, a real call and the commands to reconcile usage and billing, and it can be re-run with a new query or as a dry run that spends no credits. Discover queries should describe a tool capability, such as a company earnings report API, rather than the data wanted, and are always written in English.
Output is requested as JSON, and large responses are truncated with a download link. The CLI remembers the last discovery for 30 minutes to support numeric indices, but each call must build parameters from the selected capability's current contract and the current request, never reusing earlier business values, and time-sensitive data needs a fresh call. When comparing providers, every candidate is inspected, and probed if a current quote matters.
When your agent uses it
- Finding an external data API the agent has no tool for
- Comparing providers for a capability and falling back between them
- Reconciling QVeris usage and billing after a call
Example prompts
- “Use QVeris to find a weather forecast API and call it for tomorrow's forecast.”
- “Compare two providers for company earnings data and show which one fits.”
- “Run qveris init in dry-run mode so I can see the flow without spending credits.”
Requirements
- A QVERIS_API_KEY
- Node.js with npx to run @qverisai/cli
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- For a definite validation failure, fix parameters from the current contract or request missing input.
- Drop optional parameters only if doing so preserves the user's requested meaning.
- Switch to another compatible result only if provider, coverage, cost, and authorization constraints still hold.
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
Shell commands in SKILL.md call:
npx
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
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
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
QVeris CLI loads about 1.1k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 436 words of instructions outside code blocks.
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). 436 words, ~1,072 tokens.
Download SKILL.mdSave it as
.claude/skills/qveris-cli/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- qveris-cli
- description
- Use QVeris CLI to find and call third-party professional data and tools when existing tools are insufficient, a provider is unknown, comparison or fallback is needed, or the user requests QVeris.
Quick first run
New to QVeris? With your QVERIS_API_KEY set (create one at qveris.ai), init is a client-side first-call wizard: auth, discover, inspect, a real call, and exact usage/ledger commands to reconcile billing. It is not a server-side aggregate API.
export QVERIS_API_KEY="sk-..."
npx @qverisai/cli initRe-run anytime with --query "..." to target a different capability, or --dry-run to validate without consuming credits. Once you've seen the loop, the commands below are the day-to-day surface.
Commands
# Discover tools by capability
qveris discover "weather forecast API" --json --limit 10
# Call after selecting result 1 because its contract matches these exact fields
qveris call 1 --params '{"wfo": "BOU", "x": 50, "y": 30}' --json
# Inspect only when selection/request construction needs missing or stale details
qveris inspect 1 --json
# Probe only for parameter validation or a current quote; it does not reserve a price
qveris probe 1 --params '{"wfo": "BOU", "x": 50, "y": 30}' --checks schema,quote --json
# Validate without consuming credits
qveris call 1 --params '{"wfo": "BOU", "x": 50, "y": 30}' --dry-run --json
# Generate production code snippet (curl/python/js) — only on successful calls
qveris call 1 --params '{"wfo": "BOU", "x": 50, "y": 30}' --codegen curlAlways use --json for structured output.
Response Size
Default: 4KB (TTY) / 20KB (piped/--json). Use --max-size -1 for unlimited.
Large responses are auto-truncated with a download link for the full result.
Session Mechanism
The CLI saves the last Discover ID, query, endpoint, and result summaries for 30 minutes. This supports numeric indices and real discovery attribution; it is not semantic routing memory or a complete schema cache. A new Discover replaces the indices. Use qveris history --clear to clear it.
Build parameters from the selected capability's current contract and the user's current request. An explicit empty contract is a zero-parameter tool; an omitted contract requires Inspect. Do not copy sample business values, drop required/enum/one-of constraints, or reuse a previous entity/date value.
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.
Show full SKILL.md (185 more words)Show less
Discover Query Formulation
Describe tool capability, not data you want.
| User request | Wrong | Correct |
|---|---|---|
| "Nvidia earnings" | "Nvidia earnings" | "company earnings report API" |
| "Beijing weather" | "Beijing weather today" | "weather forecast API" |
| "BTC price" | "what is BTC price" | "cryptocurrency price API" |
Always query in English.
Tool Selection
Choose among connected tools and QVeris by task fit, data quality/freshness, cost, user constraints, and call overhead. Use QVeris when a capability is missing, the provider is unknown, comparison/fallback is needed, or the user requests it. Within Discover results, consider contract fit, provider/coverage constraints, quality, latency, and cost; do not select the first result solely by rank.
Error Recovery
Only retry when the response proves execution did not occur.
- For a definite validation failure, fix parameters from the current contract or request missing input.
- Drop optional parameters only if doing so preserves the user's requested meaning.
- Switch to another compatible result only if provider, coverage, cost, and authorization constraints still hold.
Do not repeat a paid or side-effecting Call after a timeout, network failure, or unknown execution outcome. Report the uncertainty and audit by execution_id when available.
© 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
SKILL.md and 1 other file in skills/qveris-cli of QVerisAI/qveris-agent-toolkit.
- SKILL.md
- README.md
Open the folder on GitHubat commit c7f1737
Compare with similar skills
QVeris CLI 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| QVeris CLI this skillQVerisAI/qveris-agent-toolkit | 261 | — | ~1.1k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 64 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 5 repos | ~1.2k | Automated safety check: Pass | MIT | |
| DeerFlow HTTP API Clientbytedance/deer-flow | 83k | 1 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Build MCP Serveranthropics/claude-plugins-official | 38k | 1 repos | ~3k | Automated safety check: Pass | Apache-2.0 | |
| LexGuard MCP Developer GuideSeoNaRu/lexguard-mcp | 131 | — | ~1.1k | Automated safety check: Pass | Custom licence |
Similar skills
- Official
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.
DeerFlow HTTP API Client
bytedance/deer-flow
Talks to a running DeerFlow agent platform over its HTTP API to send research questions, stream replies, check health and manage models, skills, memory and uploads.
- Official
Build MCP Server
anthropics/claude-plugins-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.
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.
Tool Registration
grandamenium/cortextos
A new tool has been added to the system and is not yet documented — agents do not know it exists or how to use it.
More from QVerisAI/qveris-agent-toolkit
QVeris Tool Discovery
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.
Related
Categories
Questions about QVeris CLI
What does QVeris CLI do?
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. The skill covers the discover, inspect and call loop of the QVeris CLI. A first-run init wizard handles authentication, discovery, inspection, a real call and the commands to reconcile usage and billing, and it can be re-run with a new query or as a dry run that spends no credits.
When should I use QVeris CLI?
QVeris CLI fits situations like: finding an external data API the agent has no tool for; comparing providers for a capability and falling back between them; reconciling QVeris usage and billing after a call.
How do I install QVeris CLI in Claude Code?
Run `npx skills add QVerisAI/qveris-agent-toolkit --skill qveris-cli -a claude-code`. Or copy the skill folder (skills/qveris-cli in QVerisAI/qveris-agent-toolkit) into .claude/skills/qveris-cli in your project. Claude Code loads it when a task matches its description.
How do I install QVeris CLI in Codex?
Run `npx skills add QVerisAI/qveris-agent-toolkit --skill qveris-cli -a codex`. Or copy the skill folder (skills/qveris-cli in QVerisAI/qveris-agent-toolkit) into .agents/skills/qveris-cli in your project. Codex loads it when a task matches its description.
Can I use QVeris CLI 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-cli -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-cli, .gemini/skills/qveris-cli, .github/skills/qveris-cli and .opencode/skills/qveris-cli in your project.
What does QVeris CLI need to run?
Going by SKILL.md and its folder, QVeris CLI needs the command-line tools its instructions call (npx) and credentials named QVERIS_API_KEY. Our summary lists: A QVERIS_API_KEY; Node.js with npx to run @qverisai/cli.
Does QVeris CLI access the network?
SKILL.md names 1 domain. As links in the text: qveris.ai. This is read from the text; nothing was executed.
Is QVeris CLI 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 CLI use?
QVeris CLI 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 CLI use?
About 1.1k tokens (SKILL.md is roughly 4.3k 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 CLI?
Skills that share tags, products or a category with QVeris CLI: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), DeerFlow HTTP API Client (bytedance/deer-flow, 83k stars) and Build MCP Server (anthropics/claude-plugins-official, 38k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains QVeris CLI?
QVerisAI (a GitHub organization) maintains it in QVerisAI/qveris-agent-toolkit, which has 261 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 6, 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.