Search Results for "http header injection"

fastapi_mcp lets you expose existing FastAPI endpoints as Model Context Protocol (MCP) tools with minimal setup, so AI agents can call your app as first-class tools. Rather than acting as a thin converter, it’s built as a native FastAPI extension that understands dependency injection, so you can reuse Depends() for authentication and authorization across your MCP tools. The server speaks directly to your app over its ASGI interface, avoiding extra HTTP hops between the MCP layer and your API, which reduces latency and simplifies deployment. A tiny bootstrap is enough to stand up an MCP server and, if desired, mount an HTTP transport for remote clients. ...

Context7 is a system that aims to inject fresh, version-specific documentation and code snippets into language model prompts, thereby avoiding reliance on outdated training data or hallucinated APIs. It’s designed to integrate with tools that support the Model Context Protocol (MCP), such as Cursor, Windsurf, and other LLM clients. When a user writes a prompt and appends something like “use context7,” the system detects the libraries or frameworks being asked about, fetches the latest...

IronClaw is a security-first, open-source personal AI assistant built in Rust and designed to keep your data fully under your control. It operates on the principle that your AI should work for you, not external vendors, ensuring all data is stored locally, encrypted, and never shared. The platform emphasizes transparency, offering auditable code with no hidden telemetry or data harvesting. IronClaw runs untrusted tools inside isolated WebAssembly (WASM) sandboxes with strict capability-based...

deprecated-generative-ai-js is a JavaScript/TypeScript client and example suite for interacting with Gemini generative APIs in web and Node.js environments. Though marked deprecated (likely superseded by newer SDKs), the repo shows how to wrap HTTP/WS endpoints, manage streaming responses, and interoperate with browser UI or server logic. The examples include chat widgets, prompt pipelines, and generalized inference utilities. It also deals with streaming cancellation, retries, backoff...

promptmap is an automated security scanner for custom LLM applications that focuses on prompt injection and related attack classes. The project supports both white-box and black-box testing, which means it can either run tests directly against a known model and system prompt configuration or attack an external HTTP endpoint without internal access. Its scanning workflow uses a dual-LLM architecture in which one model acts as the target being tested and another acts as a controller that evaluates whether an attack succeeded. ...

Sample application showcasing usage of technologies such as: * OSGi R7 Promises for asynchronous generation of transcriptions and linguistic analyses * OSGi R7 Push Stream and JAX RS Server Sent Events for push notifications of processing status * Apache Camel 2.23.1 and RabbitMQ 3.7 for asynchronous communication between services * JPA 2.1 and Hibernate 5.2.12, along with OSGi R7 JPA and Transaction Control services, for persistence layer * OSGi R7 HTTP and JAX RS Whiteboard for registering servlets, resources and REST controllers * OSGi R7 Configurator, Configuration Admin and Metatype services for automatic configuration of components * OSGi R7 Declarative Services for dependency injection * Maven automated build of Docker images * Maven automated deployment into Kubernetes cluster * RabbitMQ message broker as a StatefulSet * CockroachDB relational database as a StatefulSet See 'Code' tab for detailed information