MCP.Market

Persona MCP server

by codespar·io.github.codespar/mcp-persona·v0.2.2·271 stars

MCP server for Persona — developer-first identity verification + KYC (inquiries, accounts, reports)

B82/100grade B
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
Growing

271 stars

Reviews

Write one

Nobody has reviewed Persona yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Persona tools (20, 5 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • add_case_tag

    Add a tag to a case. Tags are operator-facing labels useful for grouping / filtering investigations (e.g. 'high-risk', 'manual-review', 'compliance-2026-q2').

  • approve_inquiry

    Mark an inquiry as approved. This records your final decision on the Persona inquiry — useful for dashboard reporting and Persona's feedback loop. Does NOT itself gate the user; you must still enforce the decision in your app.

  • create_accountwrite action

    Create a persistent Persona account — a long-lived end-user record that multiple inquiries can attach to. Enables re-use of previously verified fields and longitudinal fraud signals across sessions.

  • create_casewrite action

    Open a case — a workspace for an ongoing investigation tied to one or more inquiries / accounts. Useful for manual review, periodic re-verification, or flagged users that need operator follow-up.

  • create_inquirywrite action

    Create a Persona inquiry — a verification session bound to an inquiry template you configured in the Persona dashboard. The template defines which verifications run (document, selfie, database, phone, etc). Returns an inquiry id and (for hosted flows) a one-time link for the end user.

  • decline_inquiry

    Mark an inquiry as declined. Records your final reject decision on the Persona inquiry for reporting and feedback.

  • list_accounts

    List Persona accounts, filterable by reference-id (your internal user id) or email. Useful for looking up a persistent end-user record before creating duplicates.

  • list_cases

    List investigation cases, filterable by status, assignee, or priority. Useful for operator dashboards or batch automation over the review queue.

  • list_inquiries

    List inquiries, filterable by reference-id (your internal user id) or status. Useful for reconciling state or finding a user's inquiry history.

  • list_reports

    List reports — individual verification artifacts (e.g. watchlist, adverse media, business lookup). Filterable by account and type. Each report is a standalone verification separate from inquiry-flow verifications.

  • list_templates

    List inquiry templates configured in your Persona dashboard — returns each template's id (itmpl_...), name, and active version. Use this to discover available templates before calling create_inquiry.

  • list_webhooks

    List configured webhook subscriptions (Persona calls them 'Webhook subscriptions'). Each entry shows the URL, subscribed event types, and enabled state. Use this to audit delivery endpoints for inquiry / verification / case events.

  • redact_inquiry

    Redact an inquiry (GDPR right-to-erasure). Scrubs PII, captured images, and verification detail for this inquiry on Persona's side. Irreversible.

  • resume_inquiry

    Resume a paused inquiry — returns a fresh one-time session token / link so the end user can continue a flow that was abandoned or needs additional steps (e.g. after a 'pending' webhook).

  • retrieve_account

    Retrieve a Persona account by id, including summary PII and linked inquiries / verifications.

  • retrieve_case

    Retrieve a case by id — full detail including status, assignee, linked objects, attached fields, and tags.

  • retrieve_inquiry

    Retrieve an inquiry by id. Response includes overall status ('created' | 'pending' | 'completed' | 'expired' | 'failed' | 'needs_review' | 'approved' | 'declined') and embedded verifications / reports. Poll this to track progress.

  • retrieve_report

    Retrieve a single report by id — returns the full verification detail (matches, scores, raw source data).

  • run_reportwrite action

    Create and run a standalone Persona report — not tied to an inquiry flow. Use for ad-hoc watchlist screening, adverse media, business (KYB) lookups, address verification, or profile checks against a known identity. Pass the appropriate `report-type` plus the query fields the report needs.

  • update_accountwrite action

    Patch attributes on an existing Persona account (e.g. update address, phone, tags). Use this to keep a persistent end-user record in sync with your system of record.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan5 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 29 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Persona compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
82/100
higher than 63% of 48,255 servers
Tools
20
the typical server has 7
Tools that change things
25%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
271
more than 95% of 28,688 servers

What its tools let an agent do: 13 read · 4 create · 2 change · 1 run or deploy

Install Persona in Claude Code, Cursor or VS Code

Runs npx -y @codespar/mcp-persona on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mcp-persona -- npx -y @codespar/mcp-persona
Add to Cursor

What the publisher says

From the Persona repository's README, as published. We do not edit it. Read it on GitHub

MCP Dev LATAM 🌎 Every commerce API your AI agent needs to run a business in Latin America. Brazil 🇧🇷 · Mexico 🇲🇽 · Argentina 🇦🇷 · Colombia 🇨🇴 · Chile 🇨🇱 · Peru 🇵🇪 · plus 4 agentic payment protocols. MCP servers for LATAM commerce · live in the official MCP Registry · MIT License Machine-readable catalog: codespar.dev/api/servers Catalog · Quick Start · Agentic Protocols · All Servers · Contribute

The Problem

AI agents can write code, analyze data, and chat. But they can't operate a business — collect payments, issue invoices, ship products, or notify customers. Especially not in Latin America, where every service has its own API, auth pattern, and quirks (mTLS for BACEN Pix v2, JWT-RSA for STP-SPEI, AFIP web services, contract-gated developer portals, and on).

Meanwhile, four agentic payment protocols are shipping in parallel — checkout protocols (Stripe ACP, Google UCP), authorization layers (AP2), and micropayment rails (x402) — and none of them compose cleanly with each other or with the regional rails businesses actually run on.

MCP Dev LATAM bridges both gaps. Traditional LATAM services + the new agentic payment protocols, all accessible through a single MCP interface.

The Solution

Each MCP server in this repo wraps a real provider — payments, fiscal, logistics, messaging, banking, ERP, identity, fraud, crypto, and the agentic protocols — so your agent can operate a complete business workflow.

🛒 Customer places order
  → 💳 Agent charges via Pix (Asaas / Mercado Pago / Zoop)
  → 📄 Agent issues NFe (Nuvem Fiscal / Focus NFe / NFe.io)
  → 📦 Agent generates shipping label (Melhor Envio / Skydropx)
  → 📱 Agent sends tracking via WhatsApp (Z-API / WhatsApp Cloud)
  → 📊 Agent records in ERP (Omie / Bling / Tiny)
  → 🏦 Agent reconciles balance (Stark Bank / Itaú / BTG)

Six systems. Zero human intervention. One agent.

Agentic Payment Protocols

Four servers for the emerging agentic payment stack:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Persona: common questions

Is Persona MCP server safe?
Mostly: it is graded B (82/100). Read the Persona safety report
How do I install Persona?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Persona need an API key?
Yes. The registry entry asks for PERSONA_API_KEY.
Is Persona maintained?
The last commit was 67 days ago (2026-08-29). The latest release is v0.2.2.
What can I use instead of Persona?
Servers from other publishers that do the same job: Nautilus Compass Memory MCP server.
How does Persona compare with other MCP servers?
safety score 82/100 (higher than 63% of 48,255 servers); tools 20 (the typical server has 7); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Persona

Same job from other publishers: the closest match first, then the best rated.

  • Nautilus Compass Memory
    Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts.
    B

More from codespar →