_ registry / mcp streamable-http · checked 8h ago

catenix

https://www.catenix.com

Registry code: d1f35f6cc8ae94b2

api record

Catenix answers questions about connecting lab and point-of-care analysers to EHRs, LIS and practice systems, and about software for small labs and clinics (QC, Westgard rules, lockout, operator competency, EQA, audit trail). Use check_connectivity for 'will my analyser connect to my EHR', plan_lab_setup for several analysers plus a record system (it draws a Lab Map), recommend_lab_setup for 'what software or LIS does my lab or clinic need', search_analyzers to list supported instruments, get_ehr_integration for a record system, compare_options for LIS vs middleware or vendor comparisons, and…

endpoint
https://www.catenix.com/api/mcp
protocol
streamable-http ·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 catenix live?
Yes — it answered the hub's last check (checked 8h ago). It answered 100% of checks over the last 30 days.
Is catenix free to use?
Yes — the hub reached it with no key and no payment.
What tools does catenix have?
13 tools: get_platform_capability, check_connectivity, get_ehr_integration, compare_options, recommend_lab_setup, decode_lab_message, estimate_time_saved, request_demo, ….
Is catenix 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
100%

90 days 100%· all time 100%

latency
213ms

last good check

priced tools
0

of 13 tools

_ answered our checks, 90 days 3 checks · signed record
  • unknown → live
_ 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 13 tools
2 open 11 never probed 2 of 13 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.

  • search_analyzers open 8h ago

    Use when someone wants to know which lab or point-of-care analyzers can be interfaced, or browses by maker or test type (e.g. 'which HbA1c analyzers can connect to an EHR?', 'Abbott analyzers with an HL7 interface', 'blood gas analyzers with LIS connectivity', 'Sysmex hematology', 'Roche cobas', 'Siemens', 'Tosoh'). Returns matching analyzers with connection status, protocol and guide links. Categories: chemistry, immunoassay, blood gas, molecular, haematology, urinalysis, coagulation, HbA1c.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "properties": {
        "limit": {
          "type": "integer",
          "maximum": 50,
          "minimum": 1,
          "description": "Max results, default 25."
        },
        "query": {
          "type": "string",
          "maxLength": 120,
          "description": "Free text: model, maker, test type or protocol."
        },
        "status": {
          "enum": [
            "live",
            "driver_built",
            "guide"
          ],
          "type": "string",
          "description": "Only return analyzers with this status."
        },
        "category": {
          "type": "string",
          "maxLength": 40,
          "description": "Test category, e.g. 'haematology', 'blood gas', 'urinalysis', 'hba1c'."
        },
        "manufacturer": {
          "type": "string",
          "maxLength": 60,
          "description": "Manufacturer filter, e.g. 'Abbott', 'Sysmex', 'Roche'."
        }
      }
    }
    arguments 36 lines
  • vendor_questions open 8h ago

    Use when someone is choosing or buying a LIS, LIMS, POCT middleware or an analyzer-to-EHR interface and wants an RFP or a list of questions to ask vendors (e.g. 'what should I ask LIS vendors?', 'RFP questions for lab middleware', 'checklist for buying an HL7 interface'). Returns a copyable, vendor-neutral checklist grouped by connectivity, QC and compliance, security and privacy, data and audit trail, implementation and support, pricing, and contract and exit.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "properties": {
        "buying": {
          "enum": [
            "lis",
            "middleware",
            "interface",
            "any"
          ],
          "type": "string",
          "description": "What they are buying. Default any."
        },
        "groups": {
          "type": "array",
          "items": {
            "enum": [
              "connectivity",
              "qc",
              "security",
              "data",
              "implementation",
              "pricing",
              "exit"
            ],
            "type": "string"
          },
          "maxItems": 7,
          "description": "Only these groups. Omit for all."
        }
      }
    }
    arguments 33 lines
  • get_platform_capability unknown never probed

    Use when someone asks about software for lab quality control and compliance or running a testing clinic: QC with Westgard rules and Levey-Jennings charts, QC lockout, operator competency, EQA or proficiency testing, audit trail, CLIA, CAP or ISO 15189 readiness, reagent lot tracking, equipment maintenance and temperature logs, multi-site oversight, patient registration, reports, billing, or HL7/ASTM/POCT1-A2 interfaces. Returns the matching modules, whether each is included or an add-on, and links.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "topic"
      ],
      "properties": {
        "topic": {
          "type": "string",
          "maxLength": 160,
          "minLength": 2,
          "description": "Feature or problem, e.g. 'Westgard QC lockout', 'operator competency', 'EQA', 'audit trail'."
        }
      }
    }
    arguments 15 lines
  • check_connectivity unknown 2d ago

    Use when someone asks whether a lab or point-of-care analyzer will connect to their EHR, LIS or practice system, or how to get analyzer results into the patient record without retyping (e.g. 'will my Sysmex XP-300 work with athenahealth?', 'connect Abbott i-STAT to Epic', 'Roche cobas b 101 to SystmOne', 'Siemens CLINITEK to EMIS', 'Tosoh AIA-900 to eClinicalWorks'). Fuzzy-matches the analyzer and the record system and returns: connection status (live, driver built, connectable via standard protocol with a published guide, or custom driver needed), the analyzer protocol (HL7 v2, ASTM, POCT1-A2), the physical link, how results pass through an on-site gateway, the record-system route, what is needed on site, questions to ask any vendor, and page links. Works for unknown analyzers too. Does not interpret results.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "analyzer"
      ],
      "properties": {
        "ehr": {
          "type": "string",
          "maxLength": 120,
          "description": "EHR, LIS, LIMS or practice system, e.g. 'athena', 'eCW', 'Epic', 'SystmOne', 'EMIS Web'. Omit if not mentioned."
        },
        "country": {
          "type": "string",
          "maxLength": 60,
          "description": "Country of the site, e.g. 'UK' or 'US', if known."
        },
        "analyzer": {
          "type": "string",
          "maxLength": 120,
          "minLength": 1,
          "description": "Analyzer make and/or model as the user wrote it, e.g. 'sysmex kx21n', 'i-STAT', 'Afinion 2'."
        }
      }
    }
    arguments 25 lines
  • get_ehr_integration unknown never probed

    Use when someone asks how in-house lab or point-of-care results can be sent into a specific EHR, EMR, EPR, LIS or practice-management system, or whether a lab interface exists for it (e.g. athenahealth, eClinicalWorks, Epic, Oracle Health/Cerner, NextGen, Experity, Tebra/Kareo, SystmOne, EMIS Web, MEDITECH). Returns the route (HL7 v2, FHIR R4 or vendor API), how far that route is proven, what the practice must request from its vendor, and the guide link.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "ehr"
      ],
      "properties": {
        "ehr": {
          "type": "string",
          "maxLength": 120,
          "minLength": 1,
          "description": "Record system name as the user wrote it."
        },
        "country": {
          "type": "string",
          "maxLength": 60,
          "description": "Country, if known."
        }
      }
    }
    arguments 20 lines
  • compare_options unknown 8h ago

    Use when someone asks whether they need a LIS or POCT middleware, the difference between them, or how Catenix compares with another point-of-care data manager or results connector (Relaymed, TELCOR QML, Abbott RALS or AegisPOC, Siemens POCcelerator, Radiometer AQURE, Roche navify POC Operations, Clinisys POCT, paper or spreadsheet lab logs). Returns only what the published comparison pages say. Allowed values: catenix_vs_abbott_aegispoc, catenix_vs_abbott_rals, catenix_vs_clinisys_poct, catenix_vs_lab_logs, catenix_vs_radiometer_aqure, catenix_vs_relaymed, catenix_vs_roche_navify_poc_operations, catenix_vs_siemens_poccelerator, catenix_vs_telcor_qml, poct_middleware_alternatives, lis_vs_middleware.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "kind"
      ],
      "properties": {
        "kind": {
          "enum": [
            "catenix_vs_abbott_aegispoc",
            "catenix_vs_abbott_rals",
            "catenix_vs_clinisys_poct",
            "catenix_vs_lab_logs",
            "catenix_vs_radiometer_aqure",
            "catenix_vs_relaymed",
            "catenix_vs_roche_navify_poc_operations",
            "catenix_vs_siemens_poccelerator",
            "catenix_vs_telcor_qml",
            "poct_middleware_alternatives",
            "lis_vs_middleware"
          ],
          "type": "string",
          "description": "Which comparison: 'lis_vs_middleware', 'poct_middleware_alternatives', or 'catenix_vs_<product>'."
        }
      }
    }
    arguments 26 lines
  • recommend_lab_setup unknown never probed

    Use when someone asks what LIS, LIMS or point-of-care testing software a small lab, clinic, urgent care, occupational health provider, pharmacy, GP practice, physician office or wellness clinic should use, or how to set up analyzer connectivity, QC and reporting for their setting (e.g. 'what LIS should my small lab use?', 'do I need a LIS to get analyzer results into my EHR?', 'software for a clinic that tests blood on site'). Returns the usual architecture for that setting, the modules that fit (connectivity, QC with Westgard rules and lockout, operator competency, EQA, audit trail, reports, billing, multi-site), status of each listed analyzer, the record-system route, how setup works, what is needed on site, the pricing model (no prices are quoted), and questions to ask any vendor.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "setting"
      ],
      "properties": {
        "ehr": {
          "type": "string",
          "maxLength": 120,
          "description": "Their EHR, LIS or practice system, if known."
        },
        "country": {
          "type": "string",
          "maxLength": 60,
          "description": "Country, e.g. 'UK' or 'US'."
        },
        "setting": {
          "type": "string",
          "maxLength": 120,
          "minLength": 1,
          "description": "Type of service, e.g. 'private lab', 'urgent care', 'occupational health', 'pharmacy', 'GP practice'."
        },
        "analyzers": {
          "type": "array",
          "items": {
            "type": "string",
            "maxLength": 120
          },
          "maxItems": 20,
          "description": "Analyzers they run or plan to run."
        }
      }
    }
    arguments 34 lines
  • decode_lab_message unknown never probed

    Use when someone pastes a message from a lab analyzer, LIS, middleware or EHR interface and wants to know what it says, what a field means, or why the receiving system rejects it (e.g. 'what does this HL7 ORU mean?', 'why is my EHR rejecting this result message?', 'decode this ASTM output from my analyzer', 'is this POCT1-A2 OBS message valid?'). Accepts HL7 v2 (ORU, ORM, ACK, ADT and others), ASTM E1394 / LIS2-A2 records (H, P, O, R, C, Q, L, with or without E1381 framing and checksums) and POCT1-A2 XML. Returns a field-by-field breakdown (segment or record, field number, name, value, meaning, what an EHR or LIS usually expects) and flags common problems: wrong delimiters or segment terminators, missing MSH-9 or OBX-3 codes, numeric results without units, non-standard abnormal flags, non-LOINC codes, bad checksums. Likely patient identifiers (HL7 PID-3, PID-5, PID-7, PID-11, PID-13 and similar, ASTM patient ID, name and birthdate, POCT1-A2 patient elements) are masked in the output. Tell the user to paste only test or de-identified messages. Nothing is stored or logged. Does not interpret results.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "message"
      ],
      "properties": {
        "format": {
          "enum": [
            "auto",
            "hl7",
            "astm",
            "poct1a2"
          ],
          "type": "string",
          "description": "Leave as auto unless the user says which format it is."
        },
        "message": {
          "type": "string",
          "maxLength": 20480,
          "minLength": 3,
          "description": "The message text exactly as pasted (max 20 KB). Test or de-identified messages only."
        }
      }
    }
    arguments 25 lines
  • estimate_time_saved unknown never probed

    Use when someone wants to know how much staff time manual entry of analyzer results costs them, or would be saved by connecting analyzers to the EHR or LIS (e.g. 'we run 80 tests a day and typing each result takes 2 minutes, how much time is that?', 'is it worth interfacing our analyzers?'). Uses only the user's own numbers (tests per day, minutes of manual entry per result, sites, optionally results per test, working days and their own error rate) and returns hours per day, month and year and entries not retyped. Adds no benchmarks, prices or error statistics; without an error rate from the user it makes no error estimate.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "tests_per_day",
        "minutes_per_result"
      ],
      "properties": {
        "sites": {
          "type": "integer",
          "maximum": 10000,
          "minimum": 1,
          "description": "Number of sites, default 1."
        },
        "tests_per_day": {
          "type": "number",
          "maximum": 1000000,
          "description": "Tests per day (per site unless tests_per_day_is_total).",
          "exclusiveMinimum": 0
        },
        "results_per_test": {
          "type": "number",
          "maximum": 100,
          "description": "Results produced per test (panels give several). Default 1.",
          "exclusiveMinimum": 0
        },
        "error_rate_percent": {
          "type": "number",
          "maximum": 100,
          "minimum": 0,
          "description": "The user's own transcription error rate in percent. Omit unless the user gives it."
        },
        "minutes_per_result": {
          "type": "number",
          "maximum": 120,
          "description": "Minutes of manual entry per result.",
          "exclusiveMinimum": 0
        },
        "tests_per_day_is_total": {
          "type": "boolean",
          "description": "True if tests_per_day is the total across all sites."
        },
        "working_days_per_month": {
          "type": "number",
          "maximum": 31,
          "description": "Working days a month. Default 21.",
          "exclusiveMinimum": 0
        }
      }
    }
    arguments 50 lines
  • request_demo unknown never probed

    Sends the user's demo request to the Catenix team by email; the team replies to the address the user gives. This is the only tool that shares the user's personal details. Before calling it you MUST show the user every field you will send (name, email, organisation, country, analyzers, record system, message) and get their explicit confirmation in this conversation; then set user_confirmed to true. Never call it on your own initiative. The Catenix widget may call it only after it has shown the user every field and the user pressed Confirm and send. Do not guess missing fields: ask for them.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "name",
        "email",
        "organisation",
        "country",
        "analysers",
        "ehr",
        "user_confirmed"
      ],
      "properties": {
        "ehr": {
          "type": "string",
          "maxLength": 120,
          "minLength": 1,
          "description": "EHR, LIS or practice system ('none' if none)."
        },
        "name": {
          "type": "string",
          "maxLength": 100,
          "minLength": 1,
          "description": "The user's name."
        },
        "email": {
          "type": "string",
          "maxLength": 254,
          "minLength": 3,
          "description": "The user's work email."
        },
        "country": {
          "type": "string",
          "maxLength": 60,
          "minLength": 2,
          "description": "Country of the site."
        },
        "message": {
          "type": "string",
          "maxLength": 2000,
          "description": "Anything else the user wants to say."
        },
        "analysers": {
          "type": "string",
          "maxLength": 500,
          "minLength": 1,
          "description": "Analyzers they run, comma separated."
        },
        "organisation": {
          "type": "string",
          "maxLength": 160,
          "minLength": 1,
          "description": "Lab, clinic or company name."
        },
        "user_confirmed": {
          "type": "boolean",
          "description": "True only after the user explicitly confirmed the exact details shown to them."
        }
      }
    }
    arguments 60 lines
  • plan_lab_setup unknown never probed

    Use when someone lists the analyzers in their lab or clinic and wants a plan for getting all their results into their EHR, LIS or practice system (e.g. 'we have a Sysmex XP-300, an i-STAT and an Afinion 2, how do we connect them to athenahealth?', 'plan the interfaces for our new urgent care lab', 'what do I need on site to connect these analyzers?'). Returns one plan: per analyzer the connection status (Driver built, Connection guide, or Catenix builds the driver, usually within a couple of days), the physical link (serial, network, USB or vendor software), protocol and what is needed on site; the on-site gateway and record-system route; patient matching; and a step-by-step go-live checklist. Renders an interactive Lab Map in ChatGPT and Claude. Does not interpret results.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "analyzers"
      ],
      "properties": {
        "ehr": {
          "type": "string",
          "maxLength": 120,
          "description": "EHR, LIS or practice system, if known."
        },
        "country": {
          "type": "string",
          "maxLength": 60,
          "description": "Country, e.g. 'UK' or 'US'."
        },
        "setting": {
          "type": "string",
          "maxLength": 120,
          "description": "Type of service, e.g. 'urgent care', 'private lab', 'GP practice'."
        },
        "analyzers": {
          "type": "array",
          "items": {
            "type": "string",
            "maxLength": 120,
            "minLength": 1
          },
          "maxItems": 20,
          "minItems": 1,
          "description": "Analyzer makes and models as the user wrote them."
        }
      }
    }
    arguments 35 lines
  • check_qc_westgard unknown 35h ago

    Use when someone has quality control (QC) results for a lab or point-of-care test and wants to know whether they break Westgard rules or how they look on a Levey-Jennings chart (e.g. 'do these control values fail any Westgard rules?', 'check my QC: mean 5.0, SD 0.1, values ...', 'is this a 2-2s or 4-1s violation?'). Takes control values in run order plus the target mean and SD (or computes them from the values if the user asks) and evaluates 1-2s (warning), 1-3s, 2-2s, R-4s, 4-1s and 10x. Returns z-scores, the rule hits for each point and a plain summary, and draws a Levey-Jennings chart in ChatGPT and Claude. Up to 500 values. QC statistics only: not a clinical interpretation of any patient result.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "values"
      ],
      "properties": {
        "sd": {
          "type": "number",
          "description": "Target SD for this control lot and level.",
          "exclusiveMinimum": 0
        },
        "mean": {
          "type": "number",
          "description": "Target mean for this control lot and level."
        },
        "level": {
          "type": "string",
          "maxLength": 40,
          "description": "Control level, e.g. 'level 1'."
        },
        "units": {
          "type": "string",
          "maxLength": 30,
          "description": "Units of the values."
        },
        "values": {
          "type": "array",
          "items": {
            "type": "number"
          },
          "maxItems": 500,
          "minItems": 1,
          "description": "Control values in run order, oldest first."
        },
        "analyte": {
          "type": "string",
          "maxLength": 80,
          "description": "Test or analyte name, e.g. 'glucose'."
        },
        "compute_from_values": {
          "type": "boolean",
          "description": "True only if the user asks to compute the mean and SD from the values."
        }
      }
    }
    arguments 46 lines
  • inspection_checklist unknown never probed

    Use when someone is preparing a lab or point-of-care testing service for an inspection or accreditation and wants to know what inspectors look for (e.g. 'what do I need for a CLIA inspection?', 'CAP checklist for QC and competency', 'ISO 15189:2022 readiness', 'UK POCT governance checklist'). Returns a practical checklist (quality control, competency, EQA or proficiency testing, document control, audit trail, result reporting, equipment) with the evidence usually asked for, and which Catenix module keeps those records. General guidance, not legal or regulatory advice.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "framework"
      ],
      "properties": {
        "framework": {
          "enum": [
            "clia",
            "cap",
            "iso_15189",
            "uk_poct"
          ],
          "type": "string",
          "description": "clia (US CLIA), cap (CAP accreditation), iso_15189 (ISO 15189:2022), uk_poct (UK POCT governance, MHRA guidance)."
        }
      }
    }
    arguments 19 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 d1f35f6cc8ae94b2.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/d1f35f6cc8ae94b2/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/d1f35f6cc8ae94b2/badge.svg)](https://brick.blue/agent/d1f35f6cc8ae94b2?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.