Categories › AI & Agents › Thinking, planning & prompt tools
Deterministic physics runtime with a proof on every answer: 61 models, open and keyless over MCP.
Remote server: your requests and data go to mcp.zerotrustphysics.com. Claude Code: claude mcp add --transport http zero-trust-physics https://mcp.zerotrustphysics.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
list_cards — Lists every domain and card this connection serves, each with one sentence, and count, how many there are. against_measurement names the evidescribe_card — Describes one domain and card pair: inputs, units, bounds, step limits, reject names and meanings, advisory flags, frame slots, and worked ecompute_step — Computes one anchored step of one card and returns the state it lands on, in decimals and exact hex, with its cryptographic proof (sha384_serun_trajectory — Runs one card from a start state through segments of steps, each under its own load, and seals the run. The answer holds the outcome, the fiverify_tape — Verifies the seal of a run. Short form, which needs only what is short: request is the run_trajectory request as it was sent, with its readolist_solvers — Lists every field solver this connection serves, each with one sentence, and count, how many there are. against_measurement names the evidendescribe_solver — Describes one solver: inputs and bounds, outputs, invariants and tolerances, refusal names and meanings, the published reference, and a worksolve — Solves one field problem with one solver and seals the solution: the outcome, the result in decimals and exact hex, its invariants, the soluverify_solution — Verifies the seal of a solution. Short form, which needs only what is short: request is the solve request as it was sent (the answer's inputrun_dataset — Runs a declared plan of runs on one card, or of solves of one solver, and seals the rows under one root. A plan is a list of runs, a grid ovverify_dataset — Verifies the seal of a dataset. Short form: request is the run_dataset request as it was sent, and dataset_seal is the seal its answer gave.verify_receipt — Verifies the receipt at the end of one response against the text before it. It takes no physics permit. The receipt covers every byte of thevalidate_series — Runs a run_trajectory request (without a readout) and compares one published quantity with the agent's measurements, each at a landed step. cite — Gives how to cite a card or a solver: the service itself first (Zero-Trust Physics, its maker and its address) and the paper (https://doi.orfind_model — Finds the served model for a real thing described in plain words, such as "a lithium cell discharging in the cold". It returns the best few find_flip — Finds where an outcome changes, and gives the run on each side. request is a run_trajectory or solve request written out, its domain and cardesign_run — Designs a run: from a target end state to the loads of each segment that reach it, computed by the engine with no randomness, so the same reverify_step — Computes one anchored step of one card, as compute_step does: verify_step is the earlier name of compute_step, served for this one version bNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.