_ registry / mcp http-sse · checked 3h ago

fixsim

https://mcp.fixsim.com

Registry code: 3109b17b87851729

api record

FIXSIM is a hosted FIX protocol simulator (fixsim.com). Anyone can test FIX for free with the sandbox_* tools: sandbox_create_session returns host/port/CompIDs the user's FIX engine connects to; no account or key is needed. The fixsim_* tools drive a paying customer's own FIXSIM instances and need their FIXSIM API key (x-api-key header). An instance is a FIX engine holding sessions; the user's trading system connects to a session and FIXSIM plays the counterparty. Start with fixsim_list_instances, then fixsim_list_sessions. 'In' = messages the user's system sent to FIXSIM; 'Out' = messages…

endpoint
https://mcp.fixsim.com/mcp
protocol
http-sse ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is fixsim live?
Yes — it answered the hub's last check (checked 3h ago). It answered 99% of checks over the last 30 days.
Is fixsim free to use?
Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
What tools does fixsim have?
21 tools: fixsim_list_orders_in, fixsim_act_on_orders, sandbox_end_session, fixsim_get_order_in, sandbox_get_orders, fixsim_list_executions_out, fixsim_list_sessions, fixsim_list_orders_out, ….
Is fixsim safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
99.3%

90 days 99.5%· all time 99.5%

latency
1,139ms

last good check

priced tools
0

of 21 tools

_ answered our checks, 90 days 441 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
  • down → live
_ what it is for
topic
developer tools testing & qa
used for
  • create a free fix test session
  • fill or reject a test order
  • send a fix order to a client system
  • read fix message logs
  • list fix sessions
takes → gives
data → data
tools
13 reads8 changes data
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 21 tools
1 auth-required 20 never probed 1 of 21 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • fixsim_list_instances reads auth-required 3h ago

    List the FIXSIM instances your API key can access. An instance is a hosted FIX engine; each holds one or more FIX sessions. Start here to learn the instance names other tools need.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "apiKey": {
      "type": [
        "string",
        "null"
      ],
      "default": null,
      "description": "FIXSIM API key. Omit when the connector sends it as a header."
    }
  }
}
    arguments 13 lines
  • fixsim_list_orders_in reads unknown never probed

    Orders the user's trading system sent INTO FIXSIM on a session (FIXSIM is the counterparty). Includes ClOrdID, symbol, side, quantity, remaining quantity, order status and the raw FIX message. Optionally filter by FIX OrdStatus code (tag 39): 0 new, 1 partially filled, 2 filled, 4 canceled, 8 rejected.

    mcp-tool

    {
  "type": "object",
  "required": [
    "instance",
    "session"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 25,
      "description": "Max rows to return, newest first (default 25, max 200)"
    },
    "apiKey": {
      "type": [
        "string",
        "null"
      ],
      "default": null
    },
    "session": {
      "type": "string"
    },
    "instance": {
      "type": "string"
    },
    "orderStatus": {
      "type": [
        "string",
        "null"
      ],
      "default": null,
      "description": "Optional FIX OrdStatus (tag 39) filter"
    }
  }
}
    arguments 35 lines
  • fixsim_act_on_orders changes data unknown never probed

    Respond to orders the user's system sent into FIXSIM: acknowledge, fully or partially execute, reject, cancel remaining, expire, done-for-day, restate, or accept/reject a pending cancel/replace. FIXSIM emits the matching execution reports on the FIX session. Give one or more ClOrdIDs; for executions supply lastPx and, for a partial, lastQty.

    mcp-tool

    {
  "type": "object",
  "required": [
    "instance",
    "session",
    "action",
    "clOrdIds"
  ],
  "properties": {
    "action": {
      "type": "string",
      "description": "One of: Ack, FullyExecute, PartialExecute, CancelRemaining, DoneForDay, AckCancelOrdReplaceReq, AcceptCancelOrdReplaceReq, RejectCancelOrdReplaceReq, Reject, Delete, Restate, Expire"
    },
    "apiKey": {
      "type": [
        "string",
        "null"
      ],
      "default": null
    },
    "lastPx": {
      "type": [
        "number",
        "null"
      ],
      "default": null,
      "description": "Fill price (LastPx) for executions"
    },
    "lastQty": {
      "type": [
        "number",
        "null"
      ],
      "default": null,
      "description": "Fill quantity (LastQty) for a partial execution"
    },
    "session": {
      "type": "string"
    },
    "clOrdIds": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "ClOrdIDs (tag 11) of the inbound orders to act on"
    },
    "instance": {
      "type": "string"
    }
  }
}
    arguments 51 lines
  • sandbox_end_session changes data unknown never probed

    End a sandbox session now instead of waiting for it to expire. Frees the slot for the user's IP.

    mcp-tool

    {
  "type": "object",
  "required": [
    "sessionId"
  ],
  "properties": {
    "sessionId": {
      "type": "string",
      "format": "uuid"
    }
  }
}
    arguments 12 lines
  • fixsim_get_order_in reads unknown never probed

    Get one inbound order by ClOrdID (tag 11), including its raw FIX message and audit trail. Use this to explain why an order was rejected or what state it is in.

    mcp-tool

    {
  "type": "object",
  "required": [
    "instance",
    "session",
    "clOrdId"
  ],
  "properties": {
    "apiKey": {
      "type": [
        "string",
        "null"
      ],
      "default": null
    },
    "clOrdId": {
      "type": "string",
      "description": "ClOrdID, FIX tag 11"
    },
    "session": {
      "type": "string"
    },
    "instance": {
      "type": "string"
    }
  }
}
    arguments 27 lines
  • sandbox_get_orders reads unknown never probed

    Working orders the user's engine has sent into the sandbox session: ClOrdID, symbol, side, qty, filled, leaves, price, status.

    mcp-tool

    {
  "type": "object",
  "required": [
    "sessionId"
  ],
  "properties": {
    "sessionId": {
      "type": "string",
      "format": "uuid"
    }
  }
}
    arguments 12 lines
  • fixsim_list_executions_out reads unknown 16h ago

    Execution reports FIXSIM sent OUT on a session (acks, fills, partial fills, rejects, cancels). Pass clOrdId to see the full execution history of one order: ExecType, OrdStatus, LastPx/LastQty, CumQty, LeavesQty, AvgPx and the raw FIX.

    mcp-tool

    {
  "type": "object",
  "required": [
    "instance",
    "session"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 25,
      "description": "Max rows to return, newest first (default 25, max 200)"
    },
    "apiKey": {
      "type": [
        "string",
        "null"
      ],
      "default": null
    },
    "clOrdId": {
      "type": [
        "string",
        "null"
      ],
      "default": null,
      "description": "Optional ClOrdID (tag 11) to narrow to one order"
    },
    "session": {
      "type": "string"
    },
    "instance": {
      "type": "string"
    }
  }
}
    arguments 35 lines
  • fixsim_list_sessions reads unknown 16h ago

    List the FIX sessions on an instance with their FIX version, CompIDs, acceptor/initiator role, host/port, enabled and logged-in state, and sequence numbers.

    mcp-tool

    {
  "type": "object",
  "required": [
    "instance"
  ],
  "properties": {
    "apiKey": {
      "type": [
        "string",
        "null"
      ],
      "default": null
    },
    "instance": {
      "type": "string",
      "description": "Instance name from fixsim_list_instances"
    }
  }
}
    arguments 19 lines
  • fixsim_list_orders_out reads unknown never probed

    Orders FIXSIM sent OUT on a session (created with fixsim_send_order). Pass clOrdId to fetch one.

    mcp-tool

    {
  "type": "object",
  "required": [
    "instance",
    "session"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 25,
      "description": "Max rows to return, newest first (default 25, max 200)"
    },
    "apiKey": {
      "type": [
        "string",
        "null"
      ],
      "default": null
    },
    "clOrdId": {
      "type": [
        "string",
        "null"
      ],
      "default": null
    },
    "session": {
      "type": "string"
    },
    "instance": {
      "type": "string"
    }
  }
}
    arguments 34 lines
  • fixsim_send_raw_fix changes data unknown never probed

    Send one or more raw FIX application messages OUT on a session as given (tag=value pairs separated by | or SOH). FIXSIM supplies the session header fields (BeginString, CompIDs, MsgSeqNum, SendingTime) and the checksum. Use for message types the other tools do not cover.

    mcp-tool

    {
  "type": "object",
  "required": [
    "instance",
    "session",
    "fixMessages"
  ],
  "properties": {
    "apiKey": {
      "type": [
        "string",
        "null"
      ],
      "default": null
    },
    "session": {
      "type": "string"
    },
    "instance": {
      "type": "string"
    },
    "fixMessages": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Raw FIX messages, e.g. 35=D|11=ORD1|55=IBM|54=1|38=100|40=2|44=150.25|59=0"
    }
  }
}
    arguments 30 lines
  • fixsim_send_order changes data unknown never probed

    Have FIXSIM send a New Order Single (35=D) OUT on a session to the user's system, so they can test how their system handles inbound orders. Follow up with fixsim_list_orders_out and fixsim_list_executions_in to see what came back.

    mcp-tool

    {
  "type": "object",
  "required": [
    "instance",
    "session",
    "clOrdId",
    "symbol",
    "side",
    "orderQty",
    "ordType"
  ],
  "properties": {
    "side": {
      "type": "string",
      "description": "Side (tag 54): 1=Buy, 2=Sell, 5=Sell short"
    },
    "price": {
      "type": [
        "number",
        "null"
      ],
      "default": null,
      "description": "Price (tag 44), required for limit orders"
    },
    "apiKey": {
      "type": [
        "string",
        "null"
      ],
      "default": null
    },
    "symbol": {
      "type": "string",
      "description": "Symbol (tag 55)"
    },
    "clOrdId": {
      "type": "string",
      "description": "ClOrdID (tag 11) to assign; must be unique on the session"
    },
    "ordType": {
      "type": "string",
      "description": "OrdType (tag 40): 1=Market, 2=Limit"
    },
    "session": {
      "type": "string"
    },
    "instance": {
      "type": "string"
    },
    "orderQty": {
      "type": "number",
      "description": "OrderQty (tag 38)"
    },
    "additionalTags": {
      "type": [
        "array",
        "null"
      ],
      "items": {
        "type": [
          "object",
          "null"
        ],
        "required": [
          "tag",
          "value"
        ],
        "properties": {
          "tag": {
            "type": "integer"
          },
          "value": {
            "type": [
              "string",
              "null"
            ]
          }
        }
      },
      "default": null,
      "description": "Extra FIX tags, e.g. [{tag:59,value:\"0\"}]"
    }
  }
}
    arguments 84 lines
  • sandbox_set_autofill changes data unknown never probed

    Turn automatic fills on or off for a sandbox session. On: every order the user sends is filled immediately at the security's last price. Off (default): orders are acknowledged and wait for sandbox_act_on_order.

    mcp-tool

    {
  "type": "object",
  "required": [
    "sessionId",
    "enabled"
  ],
  "properties": {
    "enabled": {
      "type": "boolean"
    },
    "sessionId": {
      "type": "string",
      "format": "uuid"
    }
  }
}
    arguments 16 lines
  • fixsim_cancel_order_out changes data unknown never probed

    Have FIXSIM send an Order Cancel Request (35=F) for an order it previously sent out with fixsim_send_order.

    mcp-tool

    {
  "type": "object",
  "required": [
    "instance",
    "session",
    "clOrdId"
  ],
  "properties": {
    "apiKey": {
      "type": [
        "string",
        "null"
      ],
      "default": null
    },
    "clOrdId": {
      "type": "string",
      "description": "ClOrdID of the order to cancel (becomes OrigClOrdID, tag 41)"
    },
    "session": {
      "type": "string"
    },
    "instance": {
      "type": "string"
    },
    "newClOrdId": {
      "type": [
        "string",
        "null"
      ],
      "default": null,
      "description": "New ClOrdID for the cancel request (tag 11); generated if omitted"
    },
    "additionalTags": {
      "type": [
        "array",
        "null"
      ],
      "items": {
        "type": [
          "object",
          "null"
        ],
        "required": [
          "tag",
          "value"
        ],
        "properties": {
          "tag": {
            "type": "integer"
          },
          "value": {
            "type": [
              "string",
              "null"
            ]
          }
        }
      },
      "default": null
    }
  }
}
    arguments 63 lines
  • sandbox_act_on_order changes data unknown never probed

    Play the exchange for one order the user sent in: fill (full execution), partial (partial fill), reject, or cancel (cancel the remaining quantity). FIXSIM sends the matching execution report back to the user's engine.

    mcp-tool

    {
  "type": "object",
  "required": [
    "sessionId",
    "clOrdId",
    "action"
  ],
  "properties": {
    "action": {
      "type": "string",
      "description": "fill, partial, reject or cancel"
    },
    "clOrdId": {
      "type": "string",
      "description": "ClOrdID (tag 11) of the order"
    },
    "sessionId": {
      "type": "string",
      "format": "uuid"
    }
  }
}
    arguments 22 lines
  • sandbox_create_session changes data unknown never probed

    Create a free, anonymous FIX test session on the FIXSIM Developer Sandbox. No account or API key needed. Returns the connection card: host, port, the SenderCompID the user must put in tag 49, the TargetCompID for tag 56, BeginString, and the expiry (sessions last 4 hours, cap 100 application messages per day). The user's FIX engine connects as the initiator; FIXSIM is the acceptor and acknowledges every order. Keep the returned id; every other sandbox tool needs it.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "fixVersion": {
      "type": "string",
      "default": "FIX.4.4",
      "description": "FIX.4.0, FIX.4.2, FIX.4.4 (default) or FIX.5.0SP2 (rides FIXT.1.1)"
    }
  }
}
    arguments 10 lines
  • sandbox_get_session reads unknown 10h ago

    Re-fetch a sandbox session's connection card by id, including whether auto-fill is on and when it expires.

    mcp-tool

    {
  "type": "object",
  "required": [
    "sessionId"
  ],
  "properties": {
    "sessionId": {
      "type": "string",
      "format": "uuid",
      "description": "Session id from sandbox_create_session"
    }
  }
}
    arguments 13 lines
  • fixsim_get_session reads unknown 3h ago

    Get one FIX session's settings and live state (logged in?, sequence numbers, connection details).

    mcp-tool

    {
  "type": "object",
  "required": [
    "instance",
    "session"
  ],
  "properties": {
    "apiKey": {
      "type": [
        "string",
        "null"
      ],
      "default": null
    },
    "session": {
      "type": "string",
      "description": "Session name from fixsim_list_sessions"
    },
    "instance": {
      "type": "string"
    }
  }
}
    arguments 23 lines
  • fixsim_list_securities reads unknown 16h ago

    Securities (symbol, last price, CUSIP, ISIN) configured on an instance. FIXSIM prices fills from these.

    mcp-tool

    {
  "type": "object",
  "required": [
    "instance"
  ],
  "properties": {
    "apiKey": {
      "type": [
        "string",
        "null"
      ],
      "default": null
    },
    "instance": {
      "type": "string"
    }
  }
}
    arguments 18 lines
  • sandbox_get_messages reads unknown 10h ago

    The FIX message log for a sandbox session, oldest first: logons, heartbeats, orders in, execution reports out, rejects. Each message has seq, timeUtc, inbound (true = user's engine sent it), msgType, raw FIX, and parsed tag/value fields. Pass afterSeq (the last seq you saw) to fetch only new messages. Use this to explain what happened on the wire.

    mcp-tool

    {
  "type": "object",
  "required": [
    "sessionId"
  ],
  "properties": {
    "afterSeq": {
      "type": "integer",
      "default": 0,
      "description": "Return only messages with seq greater than this"
    },
    "sessionId": {
      "type": "string",
      "format": "uuid"
    }
  }
}
    arguments 17 lines
  • sandbox_get_status reads unknown 10h ago

    Is the user's FIX engine connected to the sandbox session? Returns state: connected, waiting (nobody logged on yet), disabled, or unknown.

    mcp-tool

    {
  "type": "object",
  "required": [
    "sessionId"
  ],
  "properties": {
    "sessionId": {
      "type": "string",
      "format": "uuid"
    }
  }
}
    arguments 12 lines
  • fixsim_list_executions_in reads unknown 3h ago

    Execution reports the user's system sent INTO FIXSIM on a session (when FIXSIM is the order sender and the user's system is the executing side). Optionally filter by ExecID (tag 17).

    mcp-tool

    {
  "type": "object",
  "required": [
    "instance",
    "session"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 25,
      "description": "Max rows to return, newest first (default 25, max 200)"
    },
    "apiKey": {
      "type": [
        "string",
        "null"
      ],
      "default": null
    },
    "execId": {
      "type": [
        "string",
        "null"
      ],
      "default": null,
      "description": "Optional ExecID (tag 17) filter"
    },
    "session": {
      "type": "string"
    },
    "instance": {
      "type": "string"
    }
  }
}
    arguments 35 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 3109b17b87851729.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/3109b17b87851729/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/3109b17b87851729/badge.svg)](https://brick.blue/agent/3109b17b87851729?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.