Bring Codebase Intelligence
to Pydantic AI
Learn how to connect Greptile to Pydantic AI and start using 11 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Greptile MCP Server?
Connect your Greptile account to any AI agent and unlock AI-powered codebase understanding through natural conversation.
What you can do
- AI Codebase Q&A — Ask natural language questions about one or more repositories and receive AI-generated answers with code references
- Contextual Follow-ups — Continue conversations with session context for multi-turn codebase exploration
- Semantic Code Search — Search across indexed repositories to find relevant files, functions, and code patterns
- File-Specific Search — Target searches within a specific file path for precise results
- Repository Indexing — Submit GitHub or GitLab repositories for indexing, check progress, and trigger re-indexing
- Repository Management — List all indexed repos, inspect file metadata, and remove outdated indexes
- Usage Monitoring — Track API consumption and rate limits
How it works
1. Subscribe to this server
2. Enter your Greptile API Key from the developer dashboard
3. Start querying your codebase from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Developers — understand unfamiliar codebases, find implementations, and navigate large repositories through conversation
- Code Reviewers — search for related patterns, understand code context, and trace dependencies
- Engineering Managers — get quick answers about architecture decisions, coding patterns, and technical debt
Built-in capabilities (11)
Delete indexed repository
Get file info
Check API usage
Get repository status
Index a repository
List indexed repositories
Query codebase with AI
Query with session context
Reindex a repository
Search in specific file
Search codebase
Why Pydantic AI?
Pydantic AI validates every Greptile tool response against typed schemas, catching data inconsistencies at build time. Connect 11 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Greptile integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Greptile connection logic from agent behavior for testable, maintainable code
Greptile in Pydantic AI
Greptile and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Greptile to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Greptile in Pydantic AI
The Greptile MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 11 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Greptile for Pydantic AI
Every tool call from Pydantic AI to the Greptile MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I ask natural language questions about my codebase?
Yes! The query_codebase tool sends a natural language question along with repository references and returns AI-generated answers with specific code references (file paths and line numbers). For follow-up questions, use query_with_context with the session ID from the previous response to maintain conversation continuity.
Do I need to index my repository before querying it?
Yes. Use index_repository with the remote host (github or gitlab), repository path (owner/repo), and branch name. Check indexing progress with get_repository_status. Once indexed, you can query and search the repository. Use reindex_repository to refresh the index after significant code changes.
Can I search for specific code patterns across my repositories?
Yes. The search_codebase tool performs semantic search across your indexed repositories to find relevant files and functions. For targeted results, use search_by_filepath to narrow the search to a specific file path. Use get_file_info to retrieve indexed metadata for any file.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Greptile MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai