"Transmission" matching MCP servers:

Enables RF and microwave engineers — or any MCP client — to convert impedances, analyze transmission lines and ladder circuits, synthesize L/Pi/T/stub/quarter-wave matching networks, and evaluate transistor S-parameters, stability, gain and noise circles. It also renders publication-quality Smith charts and returns human-readable summaries in English or Turkish over stdio or Streamable HTTP.

Enables AI assistants to shorten URLs with click tracking and to hand over credentials as self-destructing, one-time links whose contents are encrypted locally before transmission, so the recipient can open them exactly once. Also provides tools to list links, inspect secret metadata, revoke secrets immediately, and check account plan and rate limits.

Enables MCP clients to fill any German ELSTER tax form by Kennzahl, start or continue returns, run the portal's own checks, and review every row before transmission. It never submits; the finished form is handed off in a visible browser for the user to send.

Provides a shared context layer for AI agent teams to improve token efficiency through context deduplication and incremental state sharing. It enables multiple agents to coordinate tasks, share real-time discoveries, and manage dependencies while significantly reducing redundant data transmission.

Exposes three tools over MCP stdio that answer typed questions — yes/no, choice, and score — returning calibrated probabilities instead of prose, with offline mock answers by default and explicit egress reporting before any live transmission. Enables agents to obtain structured judgments without generating free text.

Exposes three stdio tools that let an MCP host pose typed judgments — yes/no, choice, and score — and receive calibrated probabilities rather than prose, running offline against a mock unless a credential and live provider are explicitly configured, with every outbound transmission reported on stderr.

Exposes three tools over MCP stdio that answer typed questions — yes/no, choice, and score — with calibrated probabilities instead of prose. Runs entirely offline by default, names every transmission before it happens, and only reaches a live Jev provider when credentials and provider settings are supplied.

Provides a serverless implementation of the Model Context Protocol for registering and managing tools, enabling in-memory client-server connections and credential transmission via request context.

Exposes three stdio tools that ask typed judgment questions — yes/no, choice, and score — and return calibrated probabilities instead of prose, over any MCP-speaking host. Runs on an offline mock by default, with every network transmission named before it happens and credential-gated live routes to TypeSafe or OpenRouter.

Enables MCP hosts to pose typed questions — yes/no, choice, and score — and receive calibrated probabilities instead of prose, over a stdio transport. Runs offline against a synthetic mock by default, with every transmission to a live provider named in a startup egress report.