privy-mcp-server

Provides an MCP server (Python) that connects to Privy.io’s API to manage users and wallets, including user lookup/creation/deletion, wallet creation and metadata updates, balance checks, and paginated transaction history. Intended for use with Claude Desktop and other MCP clients.

Evaluated Apr 04, 2026 (27d ago)
Homepage ↗ Repo ↗ Infrastructure mcp privy web3 wallet-management user-management python developer-tools
⚙ Agent Friendliness
69
/ 100
Can an agent use this?
🔒 Security
64
/ 100
Is it safe for agents?
⚡ Reliability
21
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
70
Documentation
75
Error Messages
0
Auth Simplicity
85
Rate Limits
70

🔒 Security

TLS Enforcement
100
Auth Strength
65
Scope Granularity
20
Dep. Hygiene
55
Secret Handling
75

Uses HTTPS to api.privy.io and instructs credentials via environment variables (reducing accidental commits). However, authentication is tied to app_id/app_secret (appears coarse-grained) and README does not discuss scope restrictions or least-privilege guidance. Destructive capabilities (delete_user) increase operational risk for agent misuse; ensure strict access controls and human-in-the-loop where appropriate.

⚡ Reliability

Uptime/SLA
0
Version Stability
30
Breaking Changes
0
Error Recovery
55
AF Security Reliability

Best When

You want an MCP-compatible interface to Privy.io for developer/ops automation, and you can run the server in a controlled environment with protected environment variables.

Avoid When

You need a strongly standardized HTTP/REST integration for broad tooling, or you require documented idempotency/retry semantics before performing write/delete operations.

Use Cases

  • Automate Privy user lookups (by DID and by wallet address) from an MCP client
  • Provision users and (optionally) embedded wallets through natural-language workflows
  • Fetch wallet balances and transaction history with pagination
  • Support internal ops tooling for wallet metadata management and audits

Not For

  • Handling production-critical flows without validating MCP tool schemas/behavior and without proper operational safeguards
  • Implementing user-facing customer workflows that require strong audit trails and human approval for destructive actions (e.g., delete)
  • Situations where you cannot securely store and protect Privy API credentials

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: HTTP Basic Authentication with custom headers (Authorization: Basic base64(app_id:app_secret) and privy-app-id header)
OAuth: No Scopes: No

Authentication is configured via PRIVY_APP_ID and PRIVY_APP_SECRET environment variables. README does not describe fine-grained scopes; likely Privy app credentials grant broad access to the Privy application.

Pricing

Free tier: No
Requires CC: No

No pricing information for the MCP server is provided; costs would primarily come from Privy.io and your hosting/runtime.

Agent Metadata

Pagination
cursor_or_page_params
Idempotent
False
Retry Guidance
Documented

Known Gotchas

  • Destructive operations exist (e.g., delete_user) and should be guarded in agent workflows; README states delete is permanent.
  • The server relies on proper environment variable loading; if env vars are missing/incorrect, authentication errors will occur.
  • Rate limits are documented at a high level; agents may need retry/backoff logic to avoid 429s.
  • Pagination is described as page-based (default 50); ensure the agent passes/consumes pagination parameters correctly.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for privy-mcp-server.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-04-04.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered