# Premiss (remote · app.premissai.com)

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

- Trust score: 87/100 (high trust)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `app.premissai.com`: 87/100 (this document), [markdown](https://verifymcp.io/servers/founders-loralabs-premiss/api-mcp-claude.md), [page](https://verifymcp.io/servers/founders-loralabs-premiss/api-mcp-claude)

## Channel facts

- Endpoint: `https://app.premissai.com/api/mcp/claude`
- Transports: `streamable-http`
- Auth: `required (not validated)`
- Version: `0.2.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1691 tokens (~130/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 74/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 10% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Premiss MCP server?

Premiss is a hosted endpoint at https://app.premissai.com/api/mcp/claude, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http founders-loralabs-premiss 'https://app.premissai.com/api/mcp/claude'
```

### Cursor

```json
{
  "mcpServers": {
    "founders-loralabs-premiss": {
      "url": "https://app.premissai.com/api/mcp/claude"
    }
  }
}
```

### VS Code

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

### Codex

```toml
[mcp_servers.founders-loralabs-premiss]
url = "https://app.premissai.com/api/mcp/claude"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "founders-loralabs-premiss": {
      "type": "remote",
      "url": "https://app.premissai.com/api/mcp/claude",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add founders-loralabs-premiss --url 'https://app.premissai.com/api/mcp/claude' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  founders-loralabs-premiss:
    url: "https://app.premissai.com/api/mcp/claude"
```

### Netclaw

```json
{
  "McpServers": {
    "founders-loralabs-premiss": {
      "Transport": "http",
      "Url": "https://app.premissai.com/api/mcp/claude"
    }
  }
}
```

### Vellum

```bash
assistant mcp add founders-loralabs-premiss -t streamable-http -u 'https://app.premissai.com/api/mcp/claude'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-02 (score 87, 0)

- [security] Stability: 0.97 → pass

### 2026-11-01 (score 87, 0)

- [security] Tool “create_strategy” rewrote its description, which is the text the model reads
- [security] Tool “get_profile” rewrote its description, which is the text the model reads
- [security] Tool “get_run_report” rewrote its description, which is the text the model reads
- [security] Tool “start_backtest” rewrote its description, which is the text the model reads
- [security] Tool “update_strategy” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 117 → 130

### 2026-10-30 (score 87, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-26 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 84, +1)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-10-21 (score 83, +1)

- [cosmetic] “get_run_data” made “limit” optional
- [cosmetic] “list_research” made “limit” optional
- [cosmetic] “search_markets” made “limit” optional
- [cosmetic] “search_markets” made “query” optional

### 2026-10-19 (score 82, +1)

- [security] The server rewrote its instructions, which are the text every model session reads

## MCP tools (13)

### `get_capabilities` (~34 tokens)

Premiss capabilities

Read this connection's available tools and supported research coverage. Does not read account data, save research, or run a simulation.

Output parameters:

- `available` (object)
- `available_tools` (array)
- `release_stage` (string)
- `research_scope` (object)
- `schema_version` (number)
- `unavailable_operations` (array)

### `get_profile` (~83 tokens)

Premiss connected workspace

Read the stable identity and workspace selected for this connection, plus the next step to take with the user. Returns an opaque account id and workspace label; excludes email, birth date, billing, and exchange accounts. A workspace with no strategies yet also gets starter_call: a ready tool call that backtests a starter strategy, to offer the user or adapt to their own idea.

Output parameters:

- `app_url` (string)
- `id` (string)
- `next_step` (string)
- `permissions` (array)
- `starter_call`
- `workspace` (object)

### `list_research` (~98 tokens)

Find saved Premiss 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.

Input parameters:

- `cursor` (string)
- `kind` (string, required)
- `limit` (integer)
- `query` (string)

Output parameters:

- `items` (array)
- `kind` (string)
- `next_cursor` (string|null)

### `get_strategy` (~51 tokens)

Read a saved 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.

Input parameters:

- `strategy_id` (string, required)

Output parameters:

- `app_url` (string)
- `files` (array)
- `id` (string)
- `interval` (string)
- `name` (string)
- `revision` (string)
- `rules`
- `symbol` (string)
- `template`
- `venue` (string)
- `version` (integer)

### `search_markets` (~51 tokens)

Find supported markets

Search the same crypto, stock and ETF directory as Premiss. Does not return prices or candles.

Input parameters:

- `asset_class` (string)
- `limit` (integer)
- `query` (string)

Output parameters:

- `markets` (array)

### `describe_market` (~30 tokens)

Check market coverage

Return supported timeframes, available history and data limitations for a market id.

Input parameters:

- `market` (string, required)

Output parameters:

- `active` (boolean)
- `assetClass` (string)
- `availability` (array)
- `availableFrom` (string|null)
- `availableTo` (string|null)
- `currency` (string)
- `exchange` (string)
- `intervals` (array)
- `market` (string)
- `name` (string)
- `notes` (array)
- `symbol` (string)

### `get_strategy_guide` (~52 tokens)

Read the strategy Python API

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.

Output parameters:

- `guide` (string)

### `create_strategy` (~142 tokens)

Save a 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. Custom code is loaded in the sandbox before saving. Returns code and revision; saving does not run a backtest.

Input parameters:

- `files` (array)
- `interval` (string, required)
- `name` (string, required)
- `request_key` (string, required): Idempotency UUID identifying one requested write and its unchanged arguments.
- `rules` (object)
- `symbol` (string, required)
- `template`

Output parameters:

- `app_url` (string)
- `files` (array)
- `id` (string)
- `interval` (string)
- `name` (string)
- `revision` (string)
- `rules`
- `symbol` (string)
- `template`
- `venue` (string)
- `version` (integer)

### `update_strategy` (~171 tokens)

Edit a strategy

Replace the complete Python package and rules of an existing strategy using its exact current saved revision. Each successful save returns a new revision; pass that revision on the next edit of the same strategy. The submitted package replaces all existing files. The code is loaded in the sandbox before saving. 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.

Input parameters:

- `files` (array, required)
- `interval` (string, required)
- `request_key` (string, required): Idempotency UUID identifying one requested write and its unchanged arguments.
- `revision` (string, required)
- `rules` (object, required)
- `strategy_id` (string, required)
- `symbol` (string, required)

Output parameters:

- `app_url` (string)
- `files` (array)
- `id` (string)
- `interval` (string)
- `name` (string)
- `revision` (string)
- `rules`
- `symbol` (string)
- `template`
- `venue` (string)
- `version` (integer)

### `start_backtest` (~242 tokens)

Start a historical 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. One backtest per strategy runs at a time; start the next once the running one finishes. 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, revision (the strategy revision to pass to start_backtest again), tested_revision (the tested code and parameters), queue (runs ahead in the shared backtest queue and an estimated wait) and poll_after_seconds, the interval before the next status check. Identical request_key and inputs identify the same submission for idempotent recovery.

Input parameters:

- `end_date` (string)
- `request_key` (string, required): Idempotency UUID identifying one requested write and its unchanged arguments.
- `revision` (string, required)
- `start_date` (string, required)
- `strategy_id` (string, required)

Output parameters:

- `app_url` (string)
- `baseline_run_id` (string)
- `end_ts` (number)
- `poll_after_seconds` (integer)
- `queue`
- `request_key` (string)
- `revision` (string)
- `run_id` (string)
- `start_ts` (number)
- `status` (string)
- `strategy_id` (string)
- `tested_revision` (string)
- `tested_rules`
- `total_bars` (integer)

### `get_run_data` (~91 tokens)

Read backtest code, trades or equity

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.

Input parameters:

- `cursor` (integer)
- `kind` (string, required)
- `limit` (integer)
- `run_id` (string, required)

Output parameters:

- `equity` (array)
- `files` (array)
- `kind` (string)
- `next_cursor` (number|null)
- `revision` (string)
- `run_id` (string)
- `trades` (array)

### `get_run_report` (~119 tokens)

Read historical or paper evidence

Read the status and bounded performance report for one run in the connected workspace. Returns the tested market, interval, revision (the tested code), strategy_revision (the strategy's current revision, accepted by start_backtest and update_strategy), 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.

Input parameters:

- `run_id` (string, required)

Output parameters:

- `app_url` (string)
- `assumptions`
- `baseline`
- `end_ts` (number|null)
- `engine_version` (integer)
- `error` (string|null)
- `interval` (string)
- `last_ts` (number|null)
- `limitations` (array)
- `metrics`
- `mode` (string)
- `queue`
- `revision` (string)
- `run_id` (string)
- `start_ts` (number)
- `status` (string)
- `strategy_id` (string)
- `strategy_revision` (string)
- `strategy_version` (integer)
- `symbol` (string)
- `tested_rules`
- `venue` (string)

### `save_research_note` (~102 tokens)

Save a 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.

Input parameters:

- `note` (string, required)
- `request_key` (string, required): Idempotency UUID identifying one requested write and its unchanged arguments.
- `revision` (string)
- `run_id` (string)
- `strategy_id` (string)
- `title` (string, required)

Output parameters:

- `app_url` (string)
- `note_id` (string)
- `saved` (boolean)
- `title` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/founders-loralabs-premiss/api-mcp-claude#diagnostics

## Score history

- 2026-11-05: 87
- 2026-11-04: 87
- 2026-11-03: 87
- 2026-11-02: 87
- 2026-11-01: 87
- 2026-10-31: 87
- 2026-10-30: 87
- 2026-10-29: 86
- 2026-10-28: 86
- 2026-10-27: 85
- 2026-10-26: 85
- 2026-10-25: 84
- 2026-10-24: 84
- 2026-10-23: 84
- 2026-10-22: 83
- 2026-10-21: 83
- 2026-10-20: 82
- 2026-10-19: 82
- 2026-10-18: 81
- 2026-10-17: 81
- 2026-10-16: 81
- 2026-10-15: 80
- 2026-10-14: 80
- 2026-10-13: 79
- 2026-10-12: 79
- 2026-10-10: 78
- 2026-10-07: 77
- 2026-10-04: 75
- 2026-10-03: 75

## Common questions

### What is the Premiss MCP server?

Premiss is an MCP server listed in the public MCP registry as io.github.founders-loralabs/premiss. Create Python strategies and backtest crypto, stocks and ETFs in Claude. Premiss account required. This page covers its hosted endpoint (https://app.premissai.com/api/mcp/claude).

### Is the Premiss MCP server safe to use?

Premiss scores 87 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Premiss MCP server expose?

Premiss exposes 13 tools: get_capabilities, get_profile, list_research, get_strategy, search_markets, and 8 more. Their descriptions and schemas cost roughly 1,266 tokens of context every time the server is loaded.

### Does the Premiss MCP server require authentication?

Yes. Premiss asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Premiss MCP server still maintained?

Premiss is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Premiss MCP server?

VerifyMCP ran 13 checks on Premiss, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://app.premissai.com/api/mcp/claude
- Website: https://app.premissai.com/integrations
- Changelog RSS feed: https://verifymcp.io/servers/founders-loralabs-premiss/api-mcp-claude.xml
- Changelog JSON feed: https://verifymcp.io/servers/founders-loralabs-premiss/api-mcp-claude/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/founders-loralabs-premiss/api-mcp-claude.json
- HTML version of this page: https://verifymcp.io/servers/founders-loralabs-premiss/api-mcp-claude