Kaiva Bridge turns your API, database or documents into a managed MCP server for Claude, ChatGPT, Cursor and VS Code. Point it at an OpenAPI or Swagger spec, an API docs link, a cURL command, a Postman collection, a GraphQL endpoint, Postgres, MySQL, MariaDB or SQL Server, spreadsheets, PDFs and other documents, or an MCP server you already run. Bridge reads the source and proposes tools, and you choose which ones your AI client sees. No code to write and nothing to run. Connect this server and your agent does the setup for you: it lists your servers, shows one, drafts a new server from an OpenAPI spec, and refreshes a server's tools when its API changes. Free plan: 10 servers and 200,000 tool calls a month, no credit card. Pricing: https://kaiv.ai/bridge/pricing Security: https://kaiv.ai/bridge/security Docs: https://kaiv.ai/bridge/docs
Scored across 4 tools
Each tool targets a distinct lifecycle stage: creating a server from a spec, retrieving one server, listing servers, and re-reading an upstream spec. There is no functional overlap, and the descriptions reinforce the differences clearly.
All tools follow a clean snake_case verb_noun pattern ending in 'server', with create/get/list/reintrospect as the verbs. Reintrospect is slightly unusual but still fits the convention.
Four tools is well-scoped for a focused server-management domain. Each tool earns its place and there is no redundancy or bloat.
The set covers the main workflow: create from an OpenAPI spec, inspect, list, and refresh after upstream changes. Explicit delete/publish tools are absent, but publishing is deliberately human-only via the console, so this is a minor gap rather than a dead end.
Turn an OpenAPI spec into a DRAFT MCP server, and report the tools it found.
Give it a public URL to an OpenAPI 3 document. Bridge fetches it, generates one typed tool per operation, and stores them UNEXPOSED. Nothing becomes callable until a human reviews the tools and publishes in the console — this tool cannot publish, and that is deliberate: exposing a tool makes somebody's API reachable, which is not a decision to automate.
Returns the server id, the proposed tools with their HTTP methods, and a console link to finish. Use when someone wants to give an agent access to an API they have a spec for.
Inputs: source_url (required), name.
Show one server: every tool it proposes, which are exposed, its state, and its gateway URL.
Use after create_server to see what was discovered, or when deciding which tools to expose. Tools are NOT exposed by default — this returns the proposal, and a human publishes it in the console. The returned console_url is where that happens.
Inputs: server_id (required).
List the MCP servers in your Kaiva Bridge workspace.
Returns each server's name, slug, state (draft or live), how many tools it proposes and how many are exposed, and its gateway URL once live. Use this to find a server before inspecting or re-introspecting it, or to answer "what have I built".
Re-read a server's source spec and refresh its tool list after the upstream API changed.
Tools that already existed keep their exposure, so a live server does not go dark. Genuinely new operations arrive UNEXPOSED — opting in to a new capability stays a deliberate human act. Operations removed upstream disappear. Use when an API has shipped new endpoints, or when a server's tools look out of date.
Inputs: server_id (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
Add one secure layer between your agents and this server.
