The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Evidra listing page.
Pacevera is a deterministic fitness decision engine exposed through the Model Context Protocol (MCP). It receives normalized training and health evidence supplied by the calling AI host, evaluates recovery and training constraints, and returns a structured decision.
The primary operation is to evaluate an existing scheduled session. A decision describes the change from the scheduled session to the resulting session:
Each decision includes the relevant evidence, applied rules, confidence, signal coverage, and limitations.
Pacevera provides the following capabilities:
keep, adjust, substitute, defer, and advance.Pacevera does not connect to these providers on behalf of the user. The calling host must obtain and normalize provider exports or API responses before passing them to an MCP tool.
The AI host is responsible for interpreting the user's request, collecting evidence, selecting tools, and presenting the result. Pacevera performs the calculations and rule evaluation; it does not call a model to generate a decision. Given the same code, rule set, and input, the result is deterministic.
| Type | Description |
|---|---|
| Recommendation | A training suggestion generated without a required prior session or plan. |
| Decision | A traceable change applied to an existing scheduled session or plan. |
decide_session requires scheduledSession to establish the prior state. If no scheduled session is provided, the tool returns no_scheduled_session rather than creating a session. Use generate_plan when a plan is required.
Decision output follows five layers:
Decision intent and resulting action are separate fields. The same intent may produce different actions depending on the user's equipment, available time, injuries, and scheduled session.
| Tool | Description |
|---|---|
assess_fitness_state | Returns recovery, readiness, muscle-group fatigue, and training-load state. |
decide_session | Evaluates a scheduled session and returns the resulting session. |
decide_exercise_substitution | Selects a replacement movement subject to injury and equipment constraints. |
generate_plan | Generates a periodized training plan. |
preview_adjust_plan | Returns a deterministic patch and diff for a caller-owned plan. |
commit_adjust_plan | Validates the plan version and applies a caller-owned patch. |
| Tool | Description |
|---|---|
get_evidence_coverage | Reports available and missing evidence signals. |
explain_decision | Returns the process-local rule and source trace for a previous decision. |
submit_outcome | Accepts an observed outcome for a prior case; storage is bounded and local to the configured environment. |
search_exercises / get_exercise | Queries the exercise catalog and graph relationships. |
search_workouts / get_workout | Queries structured workout content. |
get_user_profile | Returns caller-supplied user constraints and training settings. |
get_training_history / get_training_context | Returns training history and related context. |
Evidence is supplied by the calling host. It may include recovery measurements, vendor-computed assessments, completed workouts, scheduled sessions, goals, and constraints.
Important input rules:
signalCoverage and may lower confidence.A typical decide_session response has this shape:
Pacevera does not fill missing values with defaults. signalCoverage.recovery describes current recovery-signal availability; signalCoverage.training describes whether recent workouts include the training-load data required for fatigue calculations.
| Deployment mode | Status | Boundary |
|---|---|---|
| Local desktop extension | Available | Runs through stdio on the user's computer. The Pacevera process does not fetch provider data, persist Evidence, or make model calls. |
| User-controlled private deployment | Planned | Intended to run in a device, private network, or VPC controlled by the user or organization. |
| Hosted remote deployment | Not available | The repository contains resource-server readiness code, but production deployment, authorization infrastructure, and hosted privacy controls are not complete. |
The desktop extension has no runtime dependencies beyond the Node.js standard library. It does not use analytics, telemetry, crash reporting, provider accounts, or provider OAuth tokens.
The desktop extension processes the minimum health-related Evidence supplied by the caller for the requested fitness decision. It does not retain, sell, use for model training, or use Evidence for unrelated purposes.
The extension makes no outbound network requests and sends Evidence nowhere. On the user's own computer it does keep durable records: a bounded continuity record, and a local SQLite store holding the decisions it produced, the outcomes the user reports back, and the derived state behind them. Both are the user's to export or delete. The AI host, operating system, imported files, and any host conversation history are outside the extension's control and are governed by their respective policies.
See PRIVACY.md for the complete policy and deployment scope, and TERMS.md for the terms of use. The canonical versions are published at https://pacevera.com/privacy and https://pacevera.com/terms.
Pacevera is not a medical device and does not provide medical advice. It is intended for general fitness and training purposes only.
Pacevera is distributed as a Claude Desktop extension (.mcpb).
Download pacevera.mcpb from Releases.
Optionally verify the SHA-256 checksum published in the release notes:
In Claude Desktop, open Settings -> Extensions and install the file.
Restart Claude Desktop after installing or upgrading the extension.
The extension requires Node.js 20 or newer. Local persistence of decision traces and outcomes needs Node.js 22.5 or newer, which is where node:sqlite exists; on Node 20 or 21 the extension installs and runs without it, and reading your selected export folder for a decision is unaffected. The local plan decision is offered only once this machine holds a plan and its context, so a fresh installation does not list it — that depends on what is stored, not on the Node version.
Claude Desktop and other local MCP hosts are supported through the desktop extension. Mobile and hosted remote use cases require a remote deployment, which is not currently available for public use.
The current public release is v0.5.7, using Decision Engine 1.10.0 and base_rules@1.5.0. It includes ten public tools, bounded local continuity, personalized single-workout generation, decision traces, package validation／dry-run／rollback, and an optional local Google Health connection. The Oura and WHOOP readers were implemented from their published API specifications and have not yet been validated against real responses; Apple Health, Garmin, Google Health, and Strava readers were developed from real export files.
Pacevera is proprietary software. See LICENSE for the applicable terms.
The Claude Desktop extension includes Today’s Brief, evidence-first local export reading, and plain-language tool titles. During installation, choose Your exported health data folder and select the parent folder containing any of these optional subfolders:
Pacevera reads the selected folder locally; missing sources are reported as unavailable rather than guessed. The MCPB checksum is published in the release notes.
v0.5.7 includes an optional Google Health connection that runs on your computer. You approve it in your own browser, or by scanning a QR code with a phone; the browser route reaches Google with no Pacevera server anywhere in its path, and the QR route passes through a Pacevera relay that handles only a short-lived authorization handoff — never your health data, your tokens, or the PKCE secret that completes the exchange on your machine. Whichever route you finish cancels the other.
In v0.5.7 the connection normalizes each Google Health response in memory and writes only the resulting evidence; the provider response itself is never written to disk. You can also disconnect from inside the app: it revokes the grant at Google, deletes the stored credential, deletes the evidence earlier syncs wrote, and clears the derived records from the local store. Files you placed in the folder yourself are reported back for you to delete, never removed for you.
This connection is capped at 100 accounts, and Google will warn you that it
has not verified the app. Pacevera's Google app moved out of Testing into
Production on 2026-08-20, so an invitation is no longer required — but
Google's verification review for the health scopes is not complete. Until it is,
Google shows its own "Google hasn't verified this app" screen before you can
consent, and at most 100 accounts can authorize the connection, counted over the
app's entire lifetime. Reading your own exported folders, supplying evidence
through your AI host, and every decision tool are unaffected.
v0.5.7 fixes two ways the extension could stop answering, both of them present in v0.5.6. On a day when no fresh recovery reading arrived — the day a decision is most worth asking for — asking for today's decision from a stored plan returned nothing at all, because the local store refused to record the empty readiness the engine deliberately reports. Existing stores are repaired in place, with your rows intact. And a single very large, deeply nested request could end the extension outright, which looks from the outside like the whole connector vanishing; one bad request now fails on its own and the extension keeps running. The one rule that raises a session's intensity no longer raises it while confidence is low: thin evidence may hold a session or lower it, not add load. Coverage is also reported more plainly — the vendor scores that were actually used are named, and the coverage figure is a fraction of five kinds of evidence rather than a number that could run past its own maximum. Today's Brief now follows the language you are speaking in, and the folder reading records what it imported from Garmin without handing your folder path or file fingerprints to your AI host.
v0.5.6 reads your HRV against your own recent nights rather than a fixed reference, and where your device already computed a readiness or HRV score, that score is used instead of scoring the raw reading a second time. The raw reading is kept and reported as superseded, named alongside what replaced it, so a decision can no longer say a reading is missing when you supplied one. Connecting Google Health, syncing it, and asking for today's decision from a stored plan no longer ask you for an account identifier: Pacevera never issued one, and being asked for it again in a later conversation is what made a working connection look expired. Where this machine holds more than one profile, Pacevera asks which one by name rather than guessing.
v0.5.2 added the source chain to every reading — where Pacevera read it, and which app wrote it, so a Garmin figure synced into Apple Health is not reported as Apple Health's own. A reading whose writer the export does not name is reported as unnamed rather than guessed. Decisions also carry a small continuity record that a later conversation can hand back; Pacevera checks whether it still describes your current state and says so when it does not. It is checked, never merged: the decision always comes from the evidence held now.