fix-protocol-mcp
MCP server for parsing, validating, building and explaining FIX protocol trading messages — offline, no API keys.
README
fix-protocol-mcp
MCP server for parsing, validating, building, and explaining FIX protocol messages - the tag=value format used for orders and executions across equities, FX, and fixed-income trading.
Runs fully offline. Parsing, validation (BodyLength/CheckSum included), message construction, and the bundled FIX 4.4 field dictionary are all self-contained, no external API or network calls.
Tools
| Tool | What it does |
|---|---|
parse_fix_message |
Decode a raw FIX string into tag, field name, value, and enum meaning. Accepts SOH-, |-, or ^-delimited input. |
validate_fix_message |
Check field ordering, the standard header, BodyLength(9) and CheckSum(10) against computed values, and required/conditional fields per message type. Returns errors and warnings. |
build_fix_message |
Construct a valid FIX message from field inputs. Accepts tag numbers or field names, and enum codes or labels ("Side": "Buy"). BeginString, BodyLength, and CheckSum are computed automatically. |
explain_fix_tag |
Look up a tag's field name, data type, and enumerated values. |
Install
pip install .
This installs the fix-protocol-mcp console script (stdio MCP server).
MCP client config
{
"mcpServers": {
"fix-protocol": {
"command": "fix-protocol-mcp"
}
}
}
Running from source instead of installing:
{
"mcpServers": {
"fix-protocol": {
"command": "python",
"args": ["-m", "fix_protocol_mcp.server"],
"env": { "PYTHONPATH": "src" }
}
}
}
Examples
Parse a Logon message:
parse_fix_message("8=FIX.4.2|9=65|35=A|...|98=0|108=30|10=062|")
-> msg_type "A" (Logon), 10 fields, each decoded to name + value + enum meaning
Validate, catching a bad checksum:
validate_fix_message("8=FIX.4.2|9=65|35=A|...|10=000|")
-> { "valid": false, "checksum": {"present":"000","computed":"062","ok":false},
"errors": ["CheckSum(10)=000 does not match computed checksum 062."] }
Build an order from field names:
build_fix_message(
msg_type="NewOrderSingle",
fields={"Symbol":"AAPL","Side":"Buy","OrderQty":100,
"OrdType":"Limit","Price":"150.25","ClOrdID":"A1"})
-> 8=FIX.4.4|9=113|35=D|49=SENDER|56=TARGET|34=1|52=...|11=A1|38=100|
40=2|44=150.25|54=1|55=AAPL|60=...|10=061| (valid: true)
Explain a tag:
explain_fix_tag(40)
-> { "name": "OrdType", "type": "CHAR",
"values": [{"value":"1","meaning":"Market"}, {"value":"2","meaning":"Limit"}, ...] }
Coverage
The dictionary covers session-level messages and the order/execution workflow (Logon, Heartbeat, TestRequest, ResendRequest, Reject, SequenceReset, Logout, NewOrderSingle, OrderCancelRequest, OrderCancelReplaceRequest, ExecutionReport, OrderCancelReject), which accounts for most real FIX traffic. It's a curated subset rather than the full FIX repository - unrecognised tags and enum values surface as warnings, not hard failures.
Development
pip install -e ".[dev]"
pytest
server.py is a thin MCP wrapper around the core modules (parser,
validator, builder, dictionary, wire), which have no dependency on
the MCP SDK and can be used as a plain library:
from fix_protocol_mcp import parse, validate, build, describe_tag
License
MIT - see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.