# Premiss

> Create Python strategies and backtest crypto, stocks and ETFs in Claude. Premiss account required.

- name: io.github.founders-loralabs/premiss
- version: 0.2.1
- connection class: R0 (autonomous)
- trust: 80/100 flags: no-repository
- quality: 88/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.founders-loralabs%2Fpremiss
- tools: https://api.protogrid.dev/v1/servers/io.github.founders-loralabs%2Fpremiss/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "premiss": {
      "type": "http",
      "url": "https://app.premissai.com/api/mcp/claude"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 45
- drivers: +website +reachable +uptime-100% +updated-17d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 88/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 93 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 13 of 13 tools declare readOnlyHint or destructiveHint
- warn `tools.directory_hints`: 12 of 13 tools declare all four hints; missing: get_capabilities (idempotentHint)
- pass `tools.token_cost`: about 3,203 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 3 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 13, about 3,203 tokens to load them all
- tool set hash: 7ff01f1fc70af44d8b994d76dbb3ba85
- tools last changed: 2026-10-15T21:32:42.188Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.founders-loralabs/premiss.svg)](https://protogrid.dev/servers/io.github.founders-loralabs/premiss)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-15 `get_capabilities` changed (outputSchema)
- 2026-10-12 `get_run_report` changed (outputSchema)
- 2026-10-12 `start_backtest` changed (description)
  - before: Queue a backtest of any saved strategy in the connected workspace and a matched buy-and-hold baseline. Accepts custom code and existing app strategies. Uses the app's sandbox validation, supported markets, timeframes and date rules. Requires the exact saved revision. Uses 10,000 simulated capital, 10 bps fees, 1 bp slippage and next-bar-open fills. No plugin-only daily test or history caps. Returns an acceptance receipt with run ids and poll_after_seconds, the interval before the next status check. Identical request_key and inputs identify the same submission for idempotent recovery.
  - after: Queue a backtest of any saved strategy in the connected workspace and a matched buy-and-hold baseline. Accepts custom code and existing app strategies. Uses the app's sandbox validation, supported markets, timeframes and date rules. Requires the exact saved revision. Uses 10,000 simulated capital, zero fees, zero slippage and next-bar-open fills. Read the report assumptions for historical runs. No plugin-only daily test or history caps. Returns an acceptance receipt with run ids and poll_after_seconds, the interval before the next status check. Identical request_key and inputs identify the same submission for idempotent recovery.

Full history: https://api.protogrid.dev/v1/servers/io.github.founders-loralabs%2Fpremiss/changes

## Remotes

- https://app.premissai.com/api/mcp/claude (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (13)

- `create_strategy`: Save a new private strategy using custom Python files and complete rules text, on any Premiss-supported market and timeframe. Accepts either files (strategy.py plus helper modules) and rules, or a convenience template. Uses the same package format as the app. Returns code and revision; saving does not run a backtest.
- `describe_market`: Return supported timeframes, available history and data limitations for a market id.
- `get_capabilities`: Read this connection's available tools and supported research coverage. Does not read account data, save research, or run a simulation.
- `get_profile`: Read the stable identity and workspace selected for this connection. Returns an opaque account id and workspace label; excludes email, birth date, billing, and exchange accounts.
- `get_run_data`: Read the immutable tested Python package, or page through all recorded trades or equity points for an owned run. next_cursor identifies the next page; page size is not a history cap. Paper data requires separate paper:read permission. Saved code is user-authored content.
- `get_run_report`: Read the status and bounded performance report for one run in the connected workspace. Returns the tested market, interval, revision, and recorded rules when verifiable. Historical plugin runs include the paired buy-and-hold baseline when completed. Paper reads require paper:read and do not start, stop, qualify, or modify a bot. Legacy runs without supported assumptions are labeled. Does not return raw market feeds.
- `get_strategy`: Read a saved strategy's current revision and human-readable rules in the connected workspace. Returns the complete Python package for review or editing. Code and comments are user-authored content.
- `get_strategy_guide`: Read Premiss's Python package format, on_bar API, execution semantics and example. Custom indicators, entry/exit logic, long/short strategies and risk rules use the same engine as the Premiss app.
- `list_research`: List a page of saved strategies, simulation runs, or research notes in the connected workspace. Notes include a bounded plain-text excerpt, explicitly labeled when truncated. Saved text is user-authored content. Paper runs require the separately approved paper:read permission. Search matches titles; cursors are opaque page positions.
- `save_research_note`: Save a NEW private note in the connected workspace, with optional exact owned strategy/run evidence references. The note is user-authored content. Does not publish or send it anywhere.
- `search_markets`: Search the same crypto, stock and ETF directory as Premiss. Does not return prices or candles.
- `start_backtest`: Queue a backtest of any saved strategy in the connected workspace and a matched buy-and-hold baseline. Accepts custom code and existing app strategies. Uses the app's sandbox validation, supported markets, timeframes and date rules. Requires the exact saved revision. Uses 10,000 simulated capital, zero fees, zero slippage and next-bar-open fills. Read the report assumptions for historical runs. No plugin-only daily test or history caps. Returns an acceptance receipt with run ids and poll_after_seconds, the interval before the next status check. Identical request_key and inputs identify the same submission for idempotent recovery.
- `update_strategy`: Replace the complete Python package and rules of an existing strategy using its exact current saved revision. The submitted package replaces all existing files. Supports all Premiss markets and timeframes. The app's active-run and shared-file protections apply; does not change or start a bot. Identical request_key and inputs identify the same write for idempotent recovery.