MatLogica AADC from your coding agent: exact AAD derivatives and Greeks for Python pricers, the AADC how-tos and docs, and the AADC Tracer to follow a QuantLib or Python price to its source line
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"aadc-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# aadc-mcp <!-- mcp-name: com.matlogica/aadc-mcp --> **MatLogica's AADC engine and AADC Tracer, from your coding agent, on your own machine: exact AAD derivatives and Greeks, the AADC documentation, and a trace of where a price came from.** Reach for it when your agent is working on any of these: - adding automatic adjoint differentiation (AAD) to a Python pricer, or getting exact Greeks instead of bumping; - AAD derivatives that jump at a branch or a kink: the record shows every decision taken and how close it was to going the other way; - how to record once and replay many times, batch the evaluation, or get QuantLib sensitivities with AADC: the how-tos and the engine's own agent guide ship inside the server, and every snippet in them runs as written; - where a number in a QuantLib or Python pricing came from: which constants, which branches, which source line. `aadc-mcp` is a local [MCP](https://modelcontextprotocol.io) server. It runs over stdio inside the Python environment where the AADC packages are installed, and gives an agent in Claude Code, Cursor, Codex or any other MCP client four things: - **a measured environment check**: which packages and versions are here, whether the engine runs (it records, replays and differentiates a two-line function and checks the answer), whether QuantLib tracing attributes anything, and the pip command for whatever is missing; - **tracing of your own script with no code changes**: the script runs with recording on and leaves a tape; a QuantLib pricer written against `aadc-quantlib-tracing` needs nothing added; - **the questions a tape answers**: the constants the price depends on that nobody passed in, each at its C++ line; every decision frozen at record time and how far it was from going the other way; where a printed number was computed and the formula behind it; the source line with the recorded values written in, hash-checked against the compiled file; and a replay at new inputs that is exact whe…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.