Clarid Compliance MCP Server for Claude
Clarid AI hosted MCP server that checks bank and credit-union marketing materials for FDIC, NCUA, TILA, Reg DD, Reg Z, UDAAP, and Equal Housing compliance over streamable HTTP.
Open the source and read safety notes before installing.
Safety notes
- Marketing copy you submit is sent to Clarid for automated compliance analysis.
- Do not treat MCP output as a substitute for counsel review before publishing regulated materials.
- Confirm institution-specific policies still apply after automated checks pass.
- Avoid submitting customer PII unless your compliance program explicitly allows it.
Privacy notes
- Submitted marketing text is processed by Clarid AI under its own privacy and retention terms.
- Campaign drafts may contain product terms, rates, or institution names that should stay internal.
- Use least-privilege connectors and avoid sharing draft materials in public chat logs.
Prerequisites
- Claude Pro, Team, or Enterprise with Connectors support, or another MCP client with streamable HTTP transport.
- Marketing or compliance content you are authorized to submit for review.
- Understanding that Clarid output supports compliance workflows and is not legal advice.
- Internet access to reach the Clarid hosted endpoint.
Schema details
- Install type
- cli
- Reading time
- 4 min
- Difficulty score
- 25
- Troubleshooting
- Yes
- Breaking changes
- No
- Estimated setup
- 5 minutes
- Difficulty
- beginner
- Website
- https://clarid.ai
Full copyable content
{
"mcpServers": {
"clarid-compliance": {
"url": "https://mcp.clarid.ai/mcp",
"type": "http"
}
}
}About this resource
Overview
Clarid AI offers a hosted Model Context Protocol server for marketing compliance review aimed at community banks and credit unions. The server checks advertising and promotional materials against regulations including FDIC, NCUA, TILA, Reg DD, Reg Z, UDAAP, and Equal Housing requirements.
The service is registered in the official MCP Registry as ai.clarid/compliance with remote endpoint https://mcp.clarid.ai/mcp. Source references are published at github.com/clarid-ai/compliance-checker.
Features
- Marketing compliance checks for banking and lending advertising rules.
- Streamable HTTP transport for remote MCP clients.
- Structured compliance feedback suitable for marketing and compliance teams.
- Hosted service with no local CLI installation required.
- Complements Clarid's broader compliance platform for HMDA, fair lending, and exam readiness.
Use Cases
- Review a new deposit account landing page before publication.
- Check email campaign copy for UDAAP and disclosure issues.
- Validate social posts promoting mortgage or HELOC products.
- Screen branch signage language for Equal Housing and member-share disclaimers.
- Pre-flight website hero copy during a rebranding project.
Installation
Claude (Connectors)
- Add a custom connector under Settings → Connectors.
- Enter the MCP URL:
https://mcp.clarid.ai/mcp. - Enable the connector and submit marketing copy through chat.
Claude Code
claude mcp add --transport http clarid-compliance https://mcp.clarid.ai/mcp
claude mcp list
Other MCP clients
Add a remote HTTP connector pointing at https://mcp.clarid.ai/mcp with streamable HTTP support.
Configuration
{
"mcpServers": {
"clarid-compliance": {
"url": "https://mcp.clarid.ai/mcp",
"type": "http"
}
}
}
Examples
Landing page review
Review this homepage hero copy for FDIC, UDAAP, and Equal Housing compliance: [paste draft].
Email campaign check
Check this promotional email for Reg Z and TILA disclosure issues before we send it.
Social post screening
Does this Instagram caption for a new savings account violate NCUA advertising rules?
Security
- Clarid output is advisory; have qualified compliance staff or counsel approve final materials.
- Do not publish regulated copy based solely on automated MCP feedback.
- Restrict connector access to users who may handle draft marketing content.
Troubleshooting
Connector timeout
Retry after a few seconds; hosted endpoints may cold-start on first request.
Incomplete findings
Provide full campaign context, product type, and audience so the model can evaluate disclosures correctly.
Ambiguous product claims
Include APR/APY figures, fee schedules, and membership eligibility details when reviewing lending or deposit promotions.
Wrong regulation scope
Clarid Compliance focuses on marketing rules; use Clarid's separate HMDA validator MCP for LAR file checks.
Source citations
Add this badge to your README
Show that Clarid Compliance MCP Server for Claude is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/clarid-compliance-mcp-server)How it compares
Clarid Compliance MCP Server for Claude side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
| Field | Clarid Compliance MCP Server for Claude Clarid AI hosted MCP server that checks bank and credit-union marketing materials for FDIC, NCUA, TILA, Reg DD, Reg Z, UDAAP, and Equal Housing compliance over streamable HTTP. Open dossier | AdAdvisor MCP Server for Claude Hosted AdAdvisor MCP server with curated Meta Ads workflows for browsing creatives, launching campaigns, building audiences, and optimizing performance from Claude via streamable HTTP. Open dossier | ComplyHat MCP Server for Claude ComplyHat remote MCP server that turns AI agents into compliance documenters for SR 26-2, EU AI Act, NIST AI RMF, and ISO/IEC 42001 with OAuth and audit-ready DOCX output. Open dossier | Agentic Terminal Directory MCP Server for Claude AT Directory hosted MCP server for discovering Observer Protocol–verified merchants accepting Lightning, BOLT12, L402, and USDT agentic payments with live rail verification. Open dossier |
|---|---|---|---|---|
| Trust | ||||
| Install risk | Review first | Review first | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Category | mcp | mcp | mcp | mcp |
| Source | source-backed | source-backed | source-backed | source-backed |
| Author | Clarid AI | AdAdvisor | ComplyHat | Observer Protocol |
| Added | 2026-06-14 | 2026-06-14 | 2026-06-14 | 2026-06-14 |
| Platforms | Claude CodeCodexCursorClaude Desktop | Claude CodeClaude Desktop | Claude CodeClaude Desktop | Claude CodeClaude Desktop |
| Source repo | — | — | — | — |
| Safety notes | ✓Marketing copy you submit is sent to Clarid for automated compliance analysis. Do not treat MCP output as a substitute for counsel review before publishing regulated materials. Confirm institution-specific policies still apply after automated checks pass. Avoid submitting customer PII unless your compliance program explicitly allows it. | ✓Workflow tools can create or modify Meta Ads campaigns, ad sets, creatives, and audiences when your token has write scope. Bearer tokens grant persistent account access until revoked in AdAdvisor or Meta Business settings. Treat returned spend, conversion, and audience data as business-sensitive before sharing in chat exports. Verify AI-proposed budget or targeting changes before approving tool calls on live ad accounts. | ✓finalize report modes persist approved compliance prose with cryptographic hashes; review before finalizing. Bias, drift, and explainability tools operate on host-supplied datasets and model metadata. ComplyHat output is documentation support, not legal advice or an automatic compliance determination. Paid plans bill per MCP install seat; confirm billing scope before team-wide rollout. | ✓The directory indexes merchant claims and attestations; verify rails before sending funds. `verify_payment_endpoint` probes live endpoints but agents still pay merchants directly. Tier 1 merchants are self-attested; prefer Tier 2+ records for high-value purchases. Never share private keys or wallet seeds through MCP chat sessions. |
| Privacy notes | ✓Submitted marketing text is processed by Clarid AI under its own privacy and retention terms. Campaign drafts may contain product terms, rates, or institution names that should stay internal. Use least-privilege connectors and avoid sharing draft materials in public chat logs. | ✓Account IDs, campaign names, creative assets, and performance metrics are sent to AdAdvisor and Meta APIs. Store adv_sk_ API keys in connector headers or secrets managers, not in chat logs or source control. AdAdvisor may retain usage telemetry under its platform terms; review privacy policy before connecting production accounts. | ✓ComplyHat computes scores in memory and persists summary artifacts, not raw training data or source code. OAuth tokens and workspace data are tenant-isolated under ComplyHat's security model. Approved reports and compliance memory may contain model names, risk positions, and audit metadata. | ✓Search queries and merchant IDs may appear in Agentic Terminal logs. Payment transactions occur directly with merchants, not through the directory. Optional credentials link your agent identity for rate-limit and review features. |
| Prerequisites |
|
|
|
|
| Install | | | | |
| Config | | | | |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Signals
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.