MCP servers · bijectivelabs

TRA: self-run crypto trading desk with deterministic execution (MCP)

A self-run crypto trading desk where a rule or a language model proposes trades, and the system alone computes figures, applies limits and sends orders.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

TRA reads the market, takes one trading decision, prices the full round trip, checks the decision against limits the user declares, and then either records it or sends a single order with its stop attached. The decision can come from a rule in the user's own file, with no model involved, or from a language model that proposes a direction and levels. In both cases the system, not a model, computes every figure, applies every limit, sizes the trade and sends the order. Each decision and each refusal is kept on disk with its reason. Orders are sent through one path to every exchange that ccxt reaches, and the publisher reports end-to-end runs on six of them.

Users would reach for it to test whether a trading rule holds up before risking money. The arena replays any rule over years of recorded data, net of the user's own costs, next to buy-and-hold and a seeded random baseline. A typed judge reads the day's headlines as closed questions and can hold an entry on an adverse event. Other features include pricing of fees, spread, impact, funding and slippage before an order exists, refusal of trades whose claimed edge does not cover that cost, and read-back of unanswered orders by client order id so they are never sent twice.

Running it means operating the package from the command line, for example with `tra run` for live decisions and `tra arena` for replays. The user declares thresholds and limits in advance, and they decide the outcome. Stops and take profits are sent to the venue with the entry, or immediately after the fill where the venue does not accept them any other way.

Limitations and requirements

The publisher describes the project as experimental, and settings change between versions. The publisher has not run it with real capital, and the package ships no strategy that makes money. The user must supply their own rules, costs and limits.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    TRA

    Read-only gates of autonomous trading agents with deterministic execution: cost, data, validation.

    v0.14.0
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
neondatabase

Neon MCP Server (Postgres)

Neon's MCP server for managing Neon Postgres in plain language: create projects and branches, run queries and prepare schema migrations from your editor.

663 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
redis

Redis MCP Server

Redis's official MCP server that lets an AI assistant store, read and search data in a Redis database, including streams, JSON documents and vector indexes.

642 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
supabase-community

Supabase MCP Server

Supabase's MCP server that connects an AI assistant to your Supabase project to design tables, run queries, read configuration and look up documentation.

Data & databasesSoftware development
Updated 17 Nov 2026