# How to connect Vaquill to Claude

```json
{
  "title": "How to connect Vaquill to Claude",
  "toolkit": "Vaquill",
  "toolkit_slug": "vaquill",
  "framework": "Claude Cowork",
  "framework_slug": "claude-cowork",
  "url": "https://composio.dev/toolkits/vaquill/framework/claude-cowork",
  "markdown_url": "https://composio.dev/toolkits/vaquill/framework/claude-cowork.md",
  "updated_at": "2026-10-08T05:31:38.838Z"
}
```

## Introduction

Claude is Anthropic's AI assistant, available on the web, in the desktop app, and on mobile. Cowork is its agent for knowledge work, and it runs on all of those surfaces too. Connected to your apps, Claude can work with your files and services to accomplish complex tasks on your behalf.
This guide walks you through the easiest and most secure way to connect your Vaquill account to Claude via Composio Connect, enabling it to search US statutes on a legal question, resolve citations for a court filing, check Vaquill credits and board-change watches, and more such actions on your behalf without compromising your account security.
Setup is the same on Claude Web, Desktop, and Cowork, and you only need to do it once. The connector is tied to your account, so it's available in all three.

## Also integrate Vaquill with

- [ChatGPT](https://composio.dev/toolkits/vaquill/framework/chatgpt)
- [Hermes](https://composio.dev/toolkits/vaquill/framework/hermes-agent)
- [Atomic Agent](https://composio.dev/toolkits/vaquill/framework/atomic-agent)

## Connect Vaquill to Claude Cowork

### Connecting Vaquill to Claude Web, Desktop, and Cowork
Two ways to add the Composio connector. Pick whichever you prefer.
### 1. Add with one click
Click the button. Claude opens with the Composio connector filled in. Click Add, then go to step 2.
[Add to Claude](https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Composio&connectorUrl=https%3A%2F%2Fconnect.composio.dev%2Fmcp)
### Add manually
In Claude Desktop, click Customize in the left sidebar, then select Connectors and click the + icon at the top.
Click Add custom connector and paste in the Composio MCP server URL:

```bash
https://connect.composio.dev/mcp
```

## What is the Vaquill MCP server, and what's possible with it?

The Vaquill MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Vaquill account. It provides structured and secure access to US statutes, legal research, citation resolution, session laws, and board-change watches, so your agent can search legal sources, resolve citations, retrieve statute text, compare provisions across states, and monitor legal changes on your behalf.
- Legal research and statute search: Have your agent search statutes, regulations, constitutions, court rules, executive actions, Federal Register materials, agency guidance, adjudications, sentencing guidelines, tax treaties, and session laws.
- Citation resolution and statute details: Direct your agent to resolve Bluebook citations, retrieve statute sections and full text, find definitions and cited-by references, and identify related enactments.
- Cross-state legal comparisons: Let the agent compare a statute section with analogous provisions in other states and retrieve adjacent sections for additional context.
- Session law research: Instruct your agent to list and inspect state session laws, retrieve their text, review metadata, and track changes to the session-law registry.
- Legal change monitoring: Have your agent discover watchable legal sources, create and manage board watches, list observed changes and delivery attempts, inspect change diffs, and send test notifications.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `VAQUILL_BROWSE_STATUTE_DIVISIONS` | Browse Statute Divisions | Browse one level of a statutory hierarchy at a time. Costs 1 credit per page. |
| `VAQUILL_COMPARE_STATUTE_CROSS_STATE` | Compare Statute Cross State | Find the top analogous statutory provisions in other states for one state statute section. Costs 6 credits and supports state-statute sections only. |
| `VAQUILL_COUNT_STATUTE_SECTIONS` | Count Statute Sections | Count exact sections in a legal corpus scope before enumeration. Costs 1 credit and does not perform text search. |
| `VAQUILL_CREATE_BOARD_WATCH` | Create Board Watch | Create an active email, webhook, or dual-channel watch that immediately begins monitoring a legal corpus source and may send future external email or webhook notifications until paused or deleted. Email works on every documented plan; webhook and both require Business. The watch cap is 3 outside Business and 100 on Business, and duplicate board/channel/scope combinations return a conflict. |
| `VAQUILL_DELETE_BOARD_WATCH` | Delete Board Watch | Permanently delete a board watch and all of its delivery history. This cannot be undone. Pause the watch instead when its configuration or history must be retained. This endpoint is free. |
| `VAQUILL_GET_ADJACENT_STATUTE_SECTIONS` | Get Adjacent Statute Sections | Get the immediately adjacent sections before and after a statute section in statutory order. Costs 2 credits. |
| `VAQUILL_GET_API_CREDIT_PRICING` | Get API Credit Pricing | Get Vaquill's live credit conversion, purchase bounds, and per-operation prices without authentication or credit consumption. |
| `VAQUILL_GET_BOARD_WATCH_CHANGE_DIFF` | Get Board Watch Change Diff | Get complete old and new section text for one exact observed watch change. Call only for a change returned with has_diff=true. This is the alerts family's only metered route and normally costs 4 credits. Vaquill refunds the call when an amended change is missing either side, its resolved sides are identical, or no text resolves. |
| `VAQUILL_GET_CREDIT_BALANCE` | Get Credit Balance | Get the connected Vaquill account's spendable credits, USD balance, expiries, plan, lifetime usage, and applied request limits. This read is free and does not consume credits. |
| `VAQUILL_GET_SESSION_LAW` | Get Session Law | Get complete metadata for one US state session law by provider ID or citation. An exact provider ID costs 2 credits; citation input may also incur Vaquill's separate citation-resolution surcharge. |
| `VAQUILL_GET_SESSION_LAW_BODY` | Get Session Law Body | Get one page of a US state session law's text, with character offsets, text hash, and amendatory-markup metadata. Vaquill charges 6 credits per served page. Unavailable text is not charged; not-found, stale-cursor, and server failures are not charged or are refunded. |
| `VAQUILL_GET_SESSION_LAWS_BATCH` | Get Session Laws Batch | Get up to 50 distinct US state session laws by provider ID or citation. Vaquill charges 2 credits per law served; each citation also costs 2 resolution credits when a verdict is produced. include_body adds 6 credits per first body page served. Misses incur no batch-route charge. Validation errors are uncharged; provider 500/503 failures and resolution charges for session_not_fully_collected or lookup errors are refunded. |
| `VAQUILL_GET_STATUTE_BODY` | Get Statute Body | Get full statute text in a selected format, optionally with a subsection tree or point-in-time reconstruction. Costs 6 credits when text is returned. Ordinary unavailable text and fetch failures are refunded. Historical available:false answers are charged when the section did not yet exist or a stored-edition date is outside held coverage; unavailable observed-change reconstructions are refunded. |
| `VAQUILL_GET_STATUTE_CITED_BY` | Get Statute Cited By | Find the top USC and CFR sections that cite a statute section. Costs 2 credits; results are bounded by limit and are not pageable. |
| `VAQUILL_GET_STATUTE_DEFINITIONS` | Get Statute Definitions | Get chapter definitions governing a statute section. Costs 4 credits; no-definition and failed lookups are refunded. |
| `VAQUILL_GET_STATUTE_ENACTMENTS` | Get Statute Enactments | Get state session laws whose publisher affected-sections tables print this exact code section. This is not complete amendment history. Supported existing sections cost 1 credit, including empty answers; unsupported or missing sections and provider 500/503 failures are uncharged or refunded. Citation input adds the 2-credit resolution charge. Results are capped at the newest 200 with no continuation; inspect truncated and coverage. |
| `VAQUILL_GET_STATUTES_COVERAGE` | Get Statutes Coverage | Return Vaquill's authoritative live jurisdiction and corpus coverage matrix before choosing statute search filters. This discovery call costs no credits. |
| `VAQUILL_GET_STATUTE_SECTION` | Get Statute Section | Get metadata and source links for one US statute section by canonical section ID or resolvable citation. Costs 2 credits for an exact ID; citation input also incurs Vaquill's citation-resolution charge. |
| `VAQUILL_GET_STATUTE_SECTIONS_BATCH` | Get Statute Sections Batch | Get metadata for up to 50 statute sections in input order, with optional full text. Costs 2 credits per section returned, plus the ordinary body charge for each included body; unresolved identifiers are refunded. |
| `VAQUILL_LIST_BOARD_WATCH_CHANGES` | List Board Watch Changes | List sections observed as added, amended, or removed on a watched source. History is capture-bounded, retained for five years, and this call is free. |
| `VAQUILL_LIST_BOARD_WATCH_DELIVERIES` | List Board Watch Deliveries | List the newest persisted webhook delivery attempts and current delivery health for a board watch. History is retained for 90 days and this bounded limit-only endpoint has no second page. Email-only watches return no attempts, and synthetic test deliveries are excluded. The read is free, but meaningful history requires a webhook or both-channel watch, which requires Vaquill Business. |
| `VAQUILL_LIST_BOARD_WATCHES` | List Board Watches | List board watches owned by the connected Vaquill API-key account, including delivery destination, active state, and latest health metadata. Costs no credits. |
| `VAQUILL_LIST_SESSION_LAW_CHANGES` | List Session Law Changes | List one oldest-first page of changes to Vaquill's state session-law registry for incremental synchronization. Costs 1 credit per page, including an empty page; validation failures are not charged and provider failures are refunded. |
| `VAQUILL_LIST_SESSION_LAWS` | List Session Laws | List one page of a state's session laws with session, date, text-availability, and instrument filters. Costs 1 credit per page. Empty pages are refunded when coverage reports a wholly partial or not-held collection; complete and partly complete jurisdiction pages are charged. |
| `VAQUILL_LIST_STATUTE_CHANGES` | List Statute Changes | List capture-bounded observed change history for a statute section. This is not complete legislative history. Costs 1 credit per page. |
| `VAQUILL_LIST_WATCHABLE_BOARDS` | List Watchable Boards | List corpus sources that can be watched, including freshness, polling cadence, retrieval health, and supported scope filters. Costs no credits. |
| `VAQUILL_RESOLVE_STATUTE_CITATION` | Resolve Statute Citation | Resolve one Bluebook citation to an exact statute section. Costs 2 credits whether or not it resolves. |
| `VAQUILL_RESOLVE_STATUTE_CITATIONS_BATCH` | Resolve Statute Citations Batch | Resolve up to 50 unique Bluebook citations in one call from a raw list of up to 500 entries. Duplicates are collapsed, and each unique citation costs 2 credits. |
| `VAQUILL_SEARCH_US_STATUTES` | Search US Statutes | Search US statutes and regulations, constitutions and court rules, executive actions and Federal Register materials, agency guidance and adjudications, sentencing guidelines, tax treaties, and session laws with semantic and keyword matching. Costs 4 credits, plus 6 credits for each full body returned. |
| `VAQUILL_TEST_BOARD_WATCH` | Test Board Watch | Send one synthetic delivery through a board watch's configured channel immediately. This external side effect is limited to one test per watch every 30 seconds, is not saved in delivery history, and does not change the watch's real last-notified state. |
| `VAQUILL_UPDATE_BOARD_WATCH` | Update Board Watch | Partially update a Vaquill board watch without changing its delivery channel. Omitted fields remain unchanged. Pause/resume and email updates are available on all plans; webhook destination, signing, and outbound-auth updates require Vaquill Business. This endpoint is free. |

## Supported Triggers

None listed.

## Troubleshooting

### 1. Why does Claude not use the Composio connector for Vaquill?

The connector can show as connected, but Claude must use it in each Vaquill conversation.
- Click + at the lower left of the chat, or type /.
- Hover Connectors.
- Turn on Composio.
- Ask Claude to connect to Vaquill again.

### 2. Why does Claude show an MCP server error before Vaquill connects?

Claude can show Couldn't reach the MCP server or Authorization with the MCP server failed when you add the connector for Vaquill.
- Check that the connector URL is https://connect.composio.dev/mcp.
- Connectors run from Anthropic's cloud, so your device network is usually not the problem.
- Add the connector again from Customize > Connectors, then ask Claude to connect Vaquill.
- If it fails again, send the error and the ofid_ reference id to support@composio.dev.

### 3. Why does the Vaquill authorization link not work?

The Composio connector is one server. Your Vaquill account connects separately when Claude asks for it.
- If the browser does not open, or the link expires, ask Claude to retry the Vaquill connection.
- Composio creates a fresh Vaquill authorization link.
- Open that link in your browser and finish the Vaquill sign-in.

### 4. Why do Vaquill actions fail after they worked before?

The Vaquill connection can expire or lose permission.
- Ask Claude to inspect the Vaquill connection.
- If the connection is unhealthy, disconnect it when Claude prompts you.
- Reconnect the Vaquill account and retry the action.
- If Claude shows a permission prompt, approve it before Claude changes data in Vaquill.
- If the action still fails with a permission error, check that the connected account has that permission in Vaquill itself.

### 5. How do I switch to a different Vaquill account?

Claude can manage the Vaquill connection for you.
- Ask Claude to disconnect or delete the current Vaquill account.
- Ask Claude to connect Vaquill again.
- Open the new Composio authorization link for Vaquill.
- Sign in with the other Vaquill account in the browser.
- After the account connects, ask Claude to retry the Vaquill task.

### 6. Why is my Vaquill connection missing in Claude Desktop or on a Team plan?

The connector belongs to your Claude account, so your Vaquill connection works in Claude Web, Desktop, and Cowork.
- In Claude Desktop, open Customize > Connectors.
- Next to Composio, click ⋮ and click Clear cache.
- If Vaquill tools still do not appear, click ⋮, disconnect, remove the connector, and add it again.
- On Team or Enterprise, an Owner or Primary Owner must enable the connector before you can connect Vaquill.

## Creating MCP Server - Stand-alone vs Composio SDK

The Vaquill MCP server connects Claude Web, Desktop, and Cowork to your Vaquill account through Composio. Once connected, Claude can use the available Vaquill tools and triggers to complete tasks on your behalf.

## Complete Code

None listed.

## How to build Vaquill MCP Agent with another framework

- [ChatGPT](https://composio.dev/toolkits/vaquill/framework/chatgpt)
- [Hermes](https://composio.dev/toolkits/vaquill/framework/hermes-agent)
- [Atomic Agent](https://composio.dev/toolkits/vaquill/framework/atomic-agent)

## Related Toolkits

- [Supabase](https://composio.dev/toolkits/supabase) - Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure.
- [Codeinterpreter](https://composio.dev/toolkits/codeinterpreter) - Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms.
- [GitHub](https://composio.dev/toolkits/github) - GitHub is a code hosting platform for version control and collaborative software development. It streamlines project management, code review, and team workflows in one place.
- [1password](https://composio.dev/toolkits/_1password) - 1Password is a password manager and digital vault for storing logins, secrets, notes, and secure documents. It helps individuals and teams protect credentials, share access safely, and reduce password risk.
- [Ably](https://composio.dev/toolkits/ably) - Ably is a real-time messaging platform for live chat and data sync in modern apps. It offers global scale and rock-solid reliability for seamless, instant experiences.
- [Abuselpdb](https://composio.dev/toolkits/abuselpdb) - Abuselpdb is a central database for reporting and checking IPs linked to malicious online activity. Use it to quickly identify and report suspicious or abusive IP addresses.
- [Alchemy](https://composio.dev/toolkits/alchemy) - Alchemy is a blockchain development platform offering APIs and tools for Ethereum apps. It simplifies building and scaling Web3 projects with robust infrastructure.
- [Algolia](https://composio.dev/toolkits/algolia) - Algolia is a hosted search API that powers lightning-fast, relevant search experiences for web and mobile apps. It helps developers deliver instant, typo-tolerant, and scalable search without complex infrastructure.
- [Anakin](https://composio.dev/toolkits/anakin_io) - Anakin is a web automation platform offering scraping, crawling, search, and browser automation. Use it to extract structured data, automate site tasks, and monitor web changes reliably.
- [Anchor browser](https://composio.dev/toolkits/anchor_browser) - Anchor browser is a developer platform for AI-powered web automation. It transforms complex browser actions into easy API endpoints for streamlined web interaction.
- [Apiflash](https://composio.dev/toolkits/apiflash) - Apiflash is a website screenshot API for programmatically capturing web pages. It delivers high-quality screenshots on demand for automation, monitoring, or reporting.
- [Apiverve](https://composio.dev/toolkits/apiverve) - Apiverve delivers a suite of powerful APIs that simplify integration for developers. It's designed for reliability and scalability so you can build faster, smarter applications without the integration headache.
- [Appcircle](https://composio.dev/toolkits/appcircle) - Appcircle is an enterprise-grade mobile CI/CD platform for building, testing, and publishing mobile apps. It streamlines mobile DevOps so teams ship faster and with more confidence.
- [Appdrag](https://composio.dev/toolkits/appdrag) - Appdrag is a cloud platform for building websites, APIs, and databases with drag-and-drop tools and code editing. It accelerates development and iteration by combining hosting, database management, and low-code features in one place.
- [Appveyor](https://composio.dev/toolkits/appveyor) - AppVeyor is a cloud-based continuous integration service for building, testing, and deploying applications. It helps developers automate and streamline their software delivery pipelines.
- [Authyo](https://composio.dev/toolkits/authyo) - Authyo is a REST API service for passwordless authentication, OTP verification, session management, and transactional notifications. Use it to add secure login flows and user verification without building auth infrastructure from scratch.
- [AWS Marketplace MCP](https://composio.dev/toolkits/aws_marketplace_mcp) - AWS Marketplace MCP provides MCP access to AWS Marketplace's cloud software, data, and services catalog. Use it to discover, compare, and evaluate 30K+ AWS Marketplace listings faster.
- [Azure Monitor Activity Log](https://composio.dev/toolkits/azure_monitor_activity_log) - Azure Monitor Activity Log is Azure's service that records management and control-plane events for a subscription. Use it to audit changes, troubleshoot issues, and track resource operations across your Azure resources.
- [Backendless](https://composio.dev/toolkits/backendless) - Backendless is a backend-as-a-service platform for mobile and web apps, offering database, file storage, user authentication, and APIs. It helps developers ship scalable applications faster without managing server infrastructure.
- [Baserow](https://composio.dev/toolkits/baserow) - Baserow is an open-source no-code database platform for building collaborative data apps. It makes it easy for teams to organize data and automate workflows without writing code.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Vaquill MCP?

With a standalone Vaquill MCP server, the agents and LLMs can only access a fixed set of Vaquill tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Vaquill and many other apps based on the task at hand, all through a single MCP endpoint.

### Can I use Tool Router MCP with Claude Cowork?

Yes, you can. Claude Cowork fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Vaquill tools.

### Can I manage the permissions and scopes for Vaquill while using Tool Router?

Yes, absolutely. You can configure which Vaquill scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

### How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Vaquill data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)