Manufact

Back to submission

RJO API

mcp.dev.rjobirddog.com/mcp

Protocol: MCP 2025-11-25
Server version: 3.4.7
Supports: Tools
Resources
Prompts
Logging

Overall score

How is this score calculated?

Last reviewed at Nov 3, 2026, 10:55:51 UTC

Server metadata

Warnings50/100

Identity, discovery, and usage metadata advertised during the MCP handshake.

Stable server name

RJO API

10/10Source

Human-readable title

Add a human-readable title for clients and directories.

0/10Source

Useful description

Describe what the server helps an agent do.

0/20Source

Server version

Version 3.4.7

10/10Source

Public website

Link to a public website or documentation page.

0/10Source

Scalable or high-resolution icon

Advertise a vector or at least 128px server icon.

0/10Source

Server instructions

Usage instructions provided for agents.

20/20Source

Declared capabilities

Supports Tools, Resources, Prompts, Logging.

10/10Source

Extensions

io.modelcontextprotocol/ui

Server instructions

Read-only tools for the RJO inspections platform. Every tool is a GET; nothing here can create, modify or delete data. Call get_current_user to check your own identity and roles. Before filtering or grouping inspections, call describe_inspection_fields: some fields are only groupable after fetching, and some (lot/grower, pack date) are single-inspection only.

Discoverability

0/100

Client listings and public setup information.

mcp.json or server-card.json

Either mcp.json or an MCP Server Card declaring this endpoint passes.

No matching manifest was found at /mcp.json or /.well-known/mcp.json.

Not foundSource

Setup instructions at MCP URL

The MCP endpoint requires authentication instead of publishing public setup instructions (HTTP 401).

Not foundSource

ChatGPT

No ChatGPT listing has been confirmed yet.

UnverifiedHow to get listed

Claude

No Claude listing has been confirmed yet.

UnverifiedHow to get listed

CursorGrok BotGrok

No Cursor marketplace listing has been confirmed yet.

UnverifiedHow to get listed

Muse

No Muse listing has been confirmed yet.

UnverifiedHow to get listed

4 unverified checks. Unverified checks earn no points until confirmed.

Protocol

Pass100/100

Connection, authentication, and protocol compatibility.

MCP negotiation succeeds (v1/v2)

MCP legacy negotiation succeeded in 2569ms

Source

Tools list returns results

7 tool(s) returned

Source

Resources list responds

1 resource(s) returned

Source

Server declares tools capability

Server declares tools capability in initialize response

Source

Tools

Issues73/100

Tool definitions, annotations, and client compatibility.

Skills over MCP resources are readable

Server does not advertise the Skills over MCP extension

All tools have descriptions

All tools have non-empty descriptions

Claude Code metadata fits its 2 KB fields

1 metadata field(s) exceed Claude Code's 2 KB truncation point

How to fix: Keep each tool description and the server instructions field at or below 2 KB, and put critical guidance first.

warningclaude-code

Source

Claude tools declare applicable behavior hints

7 Claude behavior annotation issue(s) found

How to fix: For Claude directory submission, declare the applicable annotations.readOnlyHint or annotations.destructiveHint value as a boolean on every tool.

errorClaude.ai

Source

All tools have a display title

7 tool(s) missing a display title: list_dimension_values, get_scoring_rubric, describe_inspection_fields, get_inspection_detail, get_bdq_summary, aggregate_inspection_scores, get_current_user

How to fix: Set the top-level tool.title to a short human-readable label (for example, "Search catalog"). Claude directory submission requires tool titles; annotations.title remains accepted only as a legacy fallback.

errorClaude.ai

Source

All tools have OpenAI behavior hints

21 behavior annotation issue(s) found

How to fix: On each tool, declare annotations.readOnlyHint, annotations.destructiveHint, and annotations.openWorldHint as booleans. The policy review separately assesses whether their values match the tool's actual behavior.

errorChatGPT

Source

Tool names use valid characters

All tool names use valid characters

Source

Cursor tool-name budget advisory

No tool name independently exhausts Cursor's observed 60-character combined budget

Observed behavior

Tool names follow the MCP 1–128 character range

All tool names follow the MCP recommended length

Source

Tool input schemas have a valid object structure

All tool input schemas have a valid object structure

Source

Tool names follow MCP uniqueness guidance

All tool names are unique

Source

Claude tool names are within 64 characters

All tool names are within Claude's 64-character limit

Source

OpenAI file parameters use valid schemas

All declared OpenAI file parameters use reviewer-valid schemas

Source

ChatGPT tool names are unique

All tool names are unique

Source

Tool input header annotations are valid

All x-mcp-header annotations satisfy Streamable HTTP requirements

Source

Declared output schemas have a valid basic structure

0 declared output schema(s) pass basic structural validation; schemas may describe any JSON value, including arrays

Source

Tool text has no hidden control characters

No invisible or control characters found in tool-facing text

Source

MCP Apps

Skipped-

App resources, metadata, and rendering requirements.

Tool invocation metadata present

No view resources found — view checks skipped

Source

Tool-linked resource URI is readable

No view resources found — view checks skipped

Source

CSP metadata covers literal external origins

No view resources found — view checks skipped

Source

Declared domains respond

No view resources found — view checks skipped

All discovered view resources were inspected

No view resources found — view checks skipped

Source

View resource envelope is valid

No view resources found — view checks skipped

View resource metadata complete

No view resources found — view checks skipped

Source

Tool visibility metadata is valid

No view resources found — view checks skipped

Source

View resources declare a domain

No view resources found — view checks skipped

Source

Views do not request nested iframe domains

No view resources found — view checks skipped

Source

Tool documentation quality

7 tools reviewed47/100

How clearly each tool’s title, description, input and output schemas, and behavior annotations guide an agent.

list_dimension_valuesTitles 56Descriptions 97Inputs 0Annotations 0Outputs 041/100

Title56/100

Not provided

The title clearly communicates the tool’s action and subject. Keep it concise.

Description97/100

Resolve names and ids for one of RJO's reference dimensions. Use this to turn a name an operator typed ("Salinas", "Red Globe", "Dole") into the id other tools filter by, or to list what is available in a dimension. Read-only. `search` is a text filter and applies to every dimension except commodityVarieties, which instead takes `commodity_id` and/or `color`. `include_archived` adds soft-deleted rows where the dimension supports it. Passing a filter a dimension does not support is an error rather than a silent no-op. Each value carries `extra` where there is a join worth having: commodities include their market group and display group and the ids of their varieties, pickup locations include their region, and varieties include their parent commodity and colour. Buyers get only values from their own clients' approved inspections (`search` works on every dimension; no `extra`). regions and marketGroups are not available to buyers, nor are `commodity_id`, `color` and `include_archived`. In aggregate_inspection_scores a buyer can filter by name directly, without looking ids up here first.

The description explains the capability, when to use it, and what to expect.

Inputs0/100

0 of 5 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.

dimension

Not provided

Missing description. Explain what this value means and how to supply it.

Not provided

Missing description. Explain what this value means and how to supply it.

commodity_id

Not provided

Missing description. Explain what this value means and how to supply it.

color

Not provided

Missing description. Explain what this value means and how to supply it.

include_archived

Not provided

Missing description. Explain what this value means and how to supply it.

Annotations0/100

Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.

Not declared

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "list_dimension_values",
  "description": "Resolve names and ids for one of RJO's reference dimensions.\n\nUse this to turn a name an operator typed (\"Salinas\", \"Red Globe\",\n\"Dole\") into the id other tools filter by, or to list what is available\nin a dimension. Read-only.\n\n`search` is a text filter and applies to every dimension except\ncommodityVarieties, which instead takes `commodity_id` and/or `color`.\n`include_archived` adds soft-deleted rows where the dimension supports\nit. Passing a filter a dimension does not support is an error rather\nthan a silent no-op.\n\nEach value carries `extra` where there is a join worth having:\ncommodities include their market group and display group and the ids of\ntheir varieties, pickup locations include their region, and varieties\ninclude their parent commodity and colour.\n\nBuyers get only values from their own clients' approved inspections\n(`search` works on every dimension; no `extra`). regions and\nmarketGroups are not available to buyers, nor are `commodity_id`,\n`color` and `include_archived`. In aggregate_inspection_scores a buyer\ncan filter by name directly, without looking ids up here first.",
  "inputSchema": {
    "type": "object",
    "required": [
      "dimension"
    ],
    "properties": {
      "color": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "default": null
      },
      "search": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "default": null
      },
      "dimension": {
        "enum": [
          "clients",
          "shippers",
          "destinations",
          "regions",
          "pickupLocations",
          "commodities",
          "commodityVarieties",
          "displayGroups",
          "marketGroups"
        ],
        "type": "string"
      },
      "commodity_id": {
        "anyOf": [
          {
            "type": "integer"
          },
          {
            "type": "null"
          }
        ],
        "default": null
      },
      "include_archived": {
        "type": "boolean",
        "default": false
      }
    },
    "additionalProperties": false
  }
}

get_scoring_rubricTitles 67Descriptions 99Inputs 0Annotations 0Outputs 044/100

Title67/100

Not provided

The title clearly communicates the tool’s action and subject. Keep it concise.

Description99/100

Return the scoring criteria for a commodity: each criterion's name, maximum points, and the scale of point values with what each one means. Needed to interpret any inspection score — the same raw number means different things under different rubrics. Read-only. Get `commodity_id` from list_dimension_values(dimension='commodities', search=...), or from `commodityId` in get_inspection_detail. Supply `color` whenever the inspection has one. Some commodities define a separate scale per colour variant, and without the colour this falls back to the alphabetically-first variant, which may be the wrong rubric. Every response says which colour resolved the scales (`colorUsedForResolution`) and whether that was a guess (`colorWasGuessed`). When it is true the rubric may not be the right one: tell the caller so, and offer `availableColors` as the valid options to pick from. Each criterion also reports its own `scaleVariant`. Buyers: available for commodities on their own inspections.

The description explains the capability, when to use it, and what to expect.

Inputs0/100

0 of 2 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.

commodity_id

Not provided

Missing description. Explain what this value means and how to supply it.

color

Not provided

Missing description. Explain what this value means and how to supply it.

Annotations0/100

Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.

Not declared

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "get_scoring_rubric",
  "description": "Return the scoring criteria for a commodity: each criterion's name,\nmaximum points, and the scale of point values with what each one means.\n\nNeeded to interpret any inspection score — the same raw number means\ndifferent things under different rubrics. Read-only.\n\nGet `commodity_id` from list_dimension_values(dimension='commodities',\nsearch=...), or from `commodityId` in get_inspection_detail.\n\nSupply `color` whenever the inspection has one. Some commodities define\na separate scale per colour variant, and without the colour this falls\nback to the alphabetically-first variant, which may be the wrong rubric.\n\nEvery response says which colour resolved the scales\n(`colorUsedForResolution`) and whether that was a guess\n(`colorWasGuessed`). When it is true the rubric may not be the right\none: tell the caller so, and offer `availableColors` as the valid\noptions to pick from. Each criterion also reports its own\n`scaleVariant`.\n\nBuyers: available for commodities on their own inspections.",
  "inputSchema": {
    "type": "object",
    "required": [
      "commodity_id"
    ],
    "properties": {
      "color": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "default": null
      },
      "commodity_id": {
        "type": "integer"
      }
    },
    "additionalProperties": false
  }
}

describe_inspection_fieldsTitles 55Descriptions 90Inputs 100Annotations 0Outputs 065/100

Title55/100

Not provided

The title clearly communicates the tool’s action and subject. Keep it concise.

Description90/100

List every inspection field and how it can be queried: server-side filter (exact param names for /api/individual-inspections and, for buyers, client-view), present on bulk rows but only groupable after fetching, single-inspection only via get_inspection_detail, or derivable only through a join. Field names here are the ones aggregate_inspection_scores accepts in group_by and filters; `valuesFrom` says where to look their values up. Buyers: see `buyers` — what they can see, the received / in-transit split, and that their filters accept names. Call this before filtering or grouping inspections by anything, so a question about an unavailable field (e.g. grower across many inspections) is answered as "not possible" rather than from partial data. No upstream call; read-only.

The description explains the capability, when to use it, and what to expect.

Inputs100/100

This tool declares no inputs, so argument descriptions are not needed.

No input fields.

Annotations0/100

Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.

Not declared

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "describe_inspection_fields",
  "description": "List every inspection field and how it can be queried: server-side\nfilter (exact param names for /api/individual-inspections and, for\nbuyers, client-view), present on bulk rows but only groupable after\nfetching, single-inspection only via get_inspection_detail, or\nderivable only through a join. Field names here are the ones\naggregate_inspection_scores accepts in group_by and filters;\n`valuesFrom` says where to look their values up.\n\nBuyers: see `buyers` — what they can see, the received / in-transit\nsplit, and that their filters accept names.\n\nCall this before filtering or grouping inspections by anything, so a\nquestion about an unavailable field (e.g. grower across many\ninspections) is answered as \"not possible\" rather than from partial\ndata. No upstream call; read-only.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "additionalProperties": false
  }
}

get_inspection_detailTitles 51Descriptions 99Inputs 0Annotations 0Outputs 040/100

Title51/100

Not provided

The title clearly communicates the tool’s action and subject. Keep it concise.

Description99/100

Return one inspection in full: overall score, each criterion's score with its max points and scale meaning, every dimension value (commodity, variety, color, shipper, destination, pickup location, region, client, label, pack size, lot/grower, inspector, display group) and its pickup, delivery and pack dates. Use it to drill into a specific inspection once a list query has found it. It is the only tool that returns lot/grower and pack date. The overall score is computed exactly as the RJO app computes it. Read-only. Buyers get no inspector, region or status: those keys are absent, not empty. Everything a buyer can reach here is approved. An id that matches no inspection returns `{"error": "not_found", "message": ...}` rather than failing.

The description explains the capability, when to use it, and what to expect.

Inputs0/100

0 of 1 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.

inspection_id

Not provided

Missing description. Explain what this value means and how to supply it.

Annotations0/100

Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.

Not declared

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "get_inspection_detail",
  "description": "Return one inspection in full: overall score, each criterion's score\nwith its max points and scale meaning, every dimension value (commodity,\nvariety, color, shipper, destination, pickup location, region, client,\nlabel, pack size, lot/grower, inspector, display group) and its pickup,\ndelivery and pack dates.\n\nUse it to drill into a specific inspection once a list query has found\nit. It is the only tool that returns lot/grower and pack date. The\noverall score is computed exactly as the RJO app computes it. Read-only.\n\nBuyers get no inspector, region or status: those keys are absent, not\nempty. Everything a buyer can reach here is approved.\n\nAn id that matches no inspection returns\n`{\"error\": \"not_found\", \"message\": ...}` rather than failing.",
  "inputSchema": {
    "type": "object",
    "required": [
      "inspection_id"
    ],
    "properties": {
      "inspection_id": {
        "type": "integer"
      }
    },
    "additionalProperties": false
  }
}

get_bdq_summaryTitles 57Descriptions 100Inputs 0Annotations 0Outputs 042/100

Title57/100

Not provided

Add a human-readable title so users do not have to interpret the tool identifier.

Description100/100

Score summary (low/average/high) for a date range and set of clients, grouped by commodity and by display group. **Not available to the Buyer role:** RJO returns 403 for buyers (the report needs `report:read`, held by System Admin and Inspection Admin). For buyers, use aggregate_inspection_scores instead. The date range filters on when each inspection **record was created**, not its pickup or delivery date. For pickup- or delivery-date ranges, or for grouping by anything other than commodity and display group, use aggregate_inspection_scores instead. Dates accept `YYYY-MM-DD` or `M/D/YYYY` and are normalised before sending. Do not pass a quoted or padded string: RJO reads any non-ISO form in server-local time rather than UTC, which shifts the range by a day; this tool normalises to avoid that. `client_ids` is required upstream. For "all clients", pass every id from list_dimension_values(dimension='clients') — that already returns only the clients the signed-in user may see. Returns `computed` (approved inspections only, full precision) and `reportFigures` (RJO's own per-display-group numbers, exactly as the BDQ report screen shows them). The two disagree by design: `reportFigures` counts un-scored inspections as zero and rounds to whole numbers, so prefer `computed` for analysis and cite `reportFigures` only when the caller is reconciling against the app. Read-only.

The description explains the capability, when to use it, and what to expect.

Inputs0/100

0 of 3 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.

from_date

Not provided

Missing description. Explain what this value means and how to supply it.

to_date

Not provided

Missing description. Explain what this value means and how to supply it.

client_ids

Not provided

Missing description. Explain what this value means and how to supply it.

Annotations0/100

Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.

Not declared

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "get_bdq_summary",
  "description": "Score summary (low/average/high) for a date range and set of clients,\ngrouped by commodity and by display group.\n\n**Not available to the Buyer role:** RJO returns 403 for buyers (the\nreport needs `report:read`, held by System Admin and Inspection Admin).\nFor buyers, use aggregate_inspection_scores instead.\n\nThe date range filters on when each inspection **record was created**,\nnot its pickup or delivery date. For pickup- or delivery-date ranges, or\nfor grouping by anything other than commodity and display group, use\naggregate_inspection_scores instead.\n\nDates accept `YYYY-MM-DD` or `M/D/YYYY` and are normalised before\nsending. Do not pass a quoted or padded string: RJO reads any\nnon-ISO form in server-local time rather than UTC, which shifts the\nrange by a day; this tool normalises to avoid that.\n\n`client_ids` is required upstream. For \"all clients\", pass every id from\nlist_dimension_values(dimension='clients') — that already returns only\nthe clients the signed-in user may see.\n\nReturns `computed` (approved inspections only, full precision) and\n`reportFigures` (RJO's own per-display-group numbers, exactly as the BDQ\nreport screen shows them). The two disagree by design: `reportFigures`\ncounts un-scored inspections as zero and rounds to whole numbers, so\nprefer `computed` for analysis and cite `reportFigures` only when the\ncaller is reconciling against the app. Read-only.",
  "inputSchema": {
    "type": "object",
    "required": [
      "from_date",
      "to_date",
      "client_ids"
    ],
    "properties": {
      "to_date": {
        "type": "string"
      },
      "from_date": {
        "type": "string"
      },
      "client_ids": {
        "type": "array",
        "items": {
          "type": "integer"
        }
      }
    },
    "additionalProperties": false
  }
}

aggregate_inspection_scoresTitles 48Descriptions 94Inputs 0Annotations 0Outputs 038/100

Title48/100

Not provided

The title clearly communicates the tool’s action and subject. Keep it concise.

Description94/100

Overall BDQ score statistics (count, avg, min, max, stdDev) for inspections in a date range, grouped by any combination of fields and time buckets. One call answers "by shipper", "by inspector within each commodity", "by region per week", "month by month this year". Dates (inclusive, `YYYY-MM-DD` or `M/D/YYYY`) filter on `date_basis`: the pickup or delivery date. For when the inspection *record* was created, use get_bdq_summary. No limit on span; a query matching more than 20,000 inspections is refused — add filters or shorten the range. For broad multi-year comparisons, call once per year. `group_by` takes field names from describe_inspection_fields (e.g. "shipper", "commodity", "inspector", "region", "label", "pack size", "client", "market group") and the time buckets "year", "month", "week" (ISO, Monday start). Lot/grower and pack date cannot be aggregated. Empty values group under "(none)" — report its size when it matters (e.g. inspections with no region). `filters` maps field name → list. Server-filterable fields take ids from list_dimension_values (`{"shipper": [42]}`); colour takes names; other fields match values exactly, case-insensitive (`{"label": ["Peelz"]}`, `{"flagged": [true]}`). `tabs` (default approved) selects inspection status for non-buyers: unassigned, assigned, review-pending, approved, archived. Unassigned and assigned carry no score (counts only); review-pending scores are provisional; archived means deleted. Buyers always see approved inspections for their own clients only, and cannot use region. Comparing inspectors: group by inspector *within* commodity (`["commodity", "inspector"]`), since inspectors grade different produce; mention thin samples. Every rubric totals 100, so overall scores compare across commodities. `include_distribution`: adds percentiles and 10-point score bands per group (groups of 10+ only; at most 50 groups). Use for variability, consistency and threshold questions. `include_examples`: adds up to 5 real inspections per group (2 lowest, median, 2 highest) with id, score, PO and date — no extra upstream calls. Turn it on when the user asks which loads, why, what went wrong, or about variability, or when a drill-down is likely; leave it off for pure rankings and trends. Examples are ids to drill into with get_inspection_detail — never compute statistics from them. Buyers: filterable fields accept names or ids (e.g. `{"shipper": ["The Fruitist"]}`); a name that matches nothing or several values is refused with the options. Buyers see approved inspections of their own clients, split by delivery date into received (delivered before today) and in-transit (today or later); both are always scanned, and arrival (today or tomorrow) is part of in-transit. Region and market group are not available to buyers. At most 200 groups (sorted by count; the rest merged into "(other)"). Groupings with a time bucket sort chronologically and are refused rather than merged when over the cap. Read-only.

The description explains the capability, when to use it, and what to expect.

Inputs0/100

0 of 8 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.

date_from

Not provided

Missing description. Explain what this value means and how to supply it.

date_to

Not provided

Missing description. Explain what this value means and how to supply it.

date_basis

Not provided

Missing description. Explain what this value means and how to supply it.

group_by

Not provided

Missing description. Explain what this value means and how to supply it.

filters

Not provided

Missing description. Explain what this value means and how to supply it.

tabs

Not provided

Missing description. Explain what this value means and how to supply it.

include_distribution

Not provided

Missing description. Explain what this value means and how to supply it.

include_examples

Not provided

Missing description. Explain what this value means and how to supply it.

Annotations0/100

Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.

Not declared

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "aggregate_inspection_scores",
  "description": "Overall BDQ score statistics (count, avg, min, max, stdDev) for\ninspections in a date range, grouped by any combination of fields and\ntime buckets. One call answers \"by shipper\", \"by inspector within each\ncommodity\", \"by region per week\", \"month by month this year\".\n\nDates (inclusive, `YYYY-MM-DD` or `M/D/YYYY`) filter on `date_basis`:\nthe pickup or delivery date. For when the inspection *record* was\ncreated, use get_bdq_summary. No limit on span; a query matching more\nthan 20,000 inspections is refused — add filters or shorten the range.\nFor broad multi-year comparisons, call once per year.\n\n`group_by` takes field names from describe_inspection_fields (e.g.\n\"shipper\", \"commodity\", \"inspector\", \"region\", \"label\", \"pack size\",\n\"client\", \"market group\") and the time buckets \"year\", \"month\",\n\"week\" (ISO, Monday start). Lot/grower and pack date cannot be\naggregated. Empty values group under \"(none)\" — report its size when\nit matters (e.g. inspections with no region).\n\n`filters` maps field name → list. Server-filterable fields take ids\nfrom list_dimension_values (`{\"shipper\": [42]}`); colour takes names;\nother fields match values exactly, case-insensitive\n(`{\"label\": [\"Peelz\"]}`, `{\"flagged\": [true]}`).\n\n`tabs` (default approved) selects inspection status for non-buyers:\nunassigned, assigned, review-pending, approved, archived. Unassigned\nand assigned carry no score (counts only); review-pending scores are\nprovisional; archived means deleted. Buyers always see approved\ninspections for their own clients only, and cannot use region.\n\nComparing inspectors: group by inspector *within* commodity\n(`[\"commodity\", \"inspector\"]`), since inspectors grade different\nproduce; mention thin samples. Every rubric totals 100, so overall\nscores compare across commodities.\n\n`include_distribution`: adds percentiles and 10-point score bands per\ngroup (groups of 10+ only; at most 50 groups). Use for variability,\nconsistency and threshold questions.\n\n`include_examples`: adds up to 5 real inspections per group (2\nlowest, median, 2 highest) with id, score, PO and date — no extra\nupstream calls. Turn it on when the user asks which loads, why, what\nwent wrong, or about variability, or when a drill-down is likely;\nleave it off for pure rankings and trends. Examples are ids to drill\ninto with get_inspection_detail — never compute statistics from them.\n\nBuyers: filterable fields accept names or ids (e.g. `{\"shipper\":\n[\"The Fruitist\"]}`); a name that matches nothing or several values is\nrefused with the options. Buyers see approved inspections of their own\nclients, split by delivery date into received (delivered before today)\nand in-transit (today or later); both are always scanned, and arrival\n(today or tomorrow) is part of in-transit. Region and market group are\nnot available to buyers.\n\nAt most 200 groups (sorted by count; the rest merged into \"(other)\").\nGroupings with a time bucket sort chronologically and are refused\nrather than merged when over the cap. Read-only.",
  "inputSchema": {
    "type": "object",
    "required": [
      "date_from",
      "date_to",
      "date_basis",
      "group_by"
    ],
    "properties": {
      "tabs": {
        "anyOf": [
          {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          {
            "type": "null"
          }
        ],
        "default": null
      },
      "date_to": {
        "type": "string"
      },
      "filters": {
        "anyOf": [
          {
            "type": "object",
            "additionalProperties": {
              "type": "array",
              "items": {}
            }
          },
          {
            "type": "null"
          }
        ],
        "default": null
      },
      "group_by": {
        "type": "array",
        "items": {
          "type": "string"
        }
      },
      "date_from": {
        "type": "string"
      },
      "date_basis": {
        "enum": [
          "pickup",
          "delivery"
        ],
        "type": "string"
      },
      "include_examples": {
        "type": "boolean",
        "default": false
      },
      "include_distribution": {
        "type": "boolean",
        "default": false
      }
    },
    "additionalProperties": false
  }
}

get_current_userTitles 44Descriptions 83Inputs 100Annotations 0Outputs 061/100

Title44/100

Not provided

The title clearly communicates the tool’s action and subject. Keep it concise.

Description83/100

Returns the authenticated user's id, roles, and flattened permissions array based on their roles.

The description explains the capability, when to use it, and what to expect.

Inputs100/100

This tool declares no inputs, so argument descriptions are not needed.

No input fields.

Annotations0/100

Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.

Not declared

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "get_current_user",
  "description": "Returns the authenticated user's id, roles, and flattened permissions array based on their roles.",
  "inputSchema": {
    "type": "object",
    "required": [],
    "properties": {}
  }
}

Put your MCP to the test

A few tasks worth trying with this server, chosen from its reviewed tools. These have not been run.

01List dimension valuesResolve names and ids for one of RJO's reference dimensions.
02Get current userReturns the authenticated user's id, roles, and flattened permissions array based on their roles.
03Get inspection detailReturn one inspection in full: overall score, each criterion's score
04Aggregate inspection scoresOverall BDQ score statistics (count, avg, min, max, stdDev) for
05Describe inspection fieldsList every inspection field and how it can be queried: server-side

Want to run these tasks against your MCP server with us?

Test your MCP in Cloud Book a test call

Overview

Category: Data & analytics

FAQ

RJO API setup, tools, quality score, publishing readiness, and alternatives.

How do I add RJO API to Claude, ChatGPT, or Cursor?

Add RJO API to Claude, ChatGPT, or Cursor by connecting its remote MCP URL in each client's MCP settings. In Claude, add a custom connector. In ChatGPT, add an MCP app. In Cursor, add an MCP server under Settings. The MCP URL is https://mcp.dev.rjobirddog.com/mcp.

Is RJO API MCP ready for ChatGPT and Claude?

As of November 3, 2026, RJO API scores 78/100 on Manufact's MCP publishing checklist. The scan does not yet meet ChatGPT publishing checks and does not yet meet Claude publishing checks. Passing these checks does not guarantee marketplace approval.

How clear is RJO API's MCP tool documentation?

As of November 3, 2026, RJO API scores 47/100 in Manufact's review of tool titles, descriptions, input and output schemas, and behavior annotations. The review covers 7 of 7 discovered tools. The quality score measures documentation clarity; runtime behavior and marketplace readiness require separate checks.

What are the best alternatives to RJO API?

As of November 3, 2026, alternatives to RJO API in data-analytics on the Manufact MCP leaderboard include ClickHouse Cloud MCP Server, Ploti, ClickHouse Cloud MCP Server, ClickHouse Cloud MCP Server, and Funraise Taiwan Real Estate.

How can RJO API improve its MCP documentation?

aggregate_inspection_scores is the lowest-scoring reviewed tool at 38/100. 0 of 8 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values. Open its review for feedback and a copyable fix prompt, then rerun the documentation review after updating your tool metadata.

Not your MCP?

Review any public or OAuth MCP server for protocol compatibility, tool documentation, and ChatGPT and Claude publishing readiness. No account required.

Get your MCP score

Back to leaderboard

Opening your score report…

Title48/100

Not provided

The title clearly communicates the tool’s action and subject. Keep it concise.

Description94/100

The description explains the capability, when to use it, and what to expect.

Inputs0/100

0 of 8 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.

date_from

Not provided

Missing description. Explain what this value means and how to supply it.

date_to

Not provided

Missing description. Explain what this value means and how to supply it.

date_basis

Not provided

Missing description. Explain what this value means and how to supply it.

group_by

Not provided

Missing description. Explain what this value means and how to supply it.

filters

Not provided

Missing description. Explain what this value means and how to supply it.

tabs

Not provided

Missing description. Explain what this value means and how to supply it.

include_distribution

Not provided

Missing description. Explain what this value means and how to supply it.

include_examples

Not provided

Missing description. Explain what this value means and how to supply it.

Annotations0/100

Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.

Not declared

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "aggregate_inspection_scores",
  "description": "Overall BDQ score statistics (count, avg, min, max, stdDev) for\ninspections in a date range, grouped by any combination of fields and\ntime buckets. One call answers \"by shipper\", \"by inspector within each\ncommodity\", \"by region per week\", \"month by month this year\".\n\nDates (inclusive, `YYYY-MM-DD` or `M/D/YYYY`) filter on `date_basis`:\nthe pickup or delivery date. For when the inspection *record* was\ncreated, use get_bdq_summary. No limit on span; a query matching more\nthan 20,000 inspections is refused — add filters or shorten the range.\nFor broad multi-year comparisons, call once per year.\n\n`group_by` takes field names from describe_inspection_fields (e.g.\n\"shipper\", \"commodity\", \"inspector\", \"region\", \"label\", \"pack size\",\n\"client\", \"market group\") and the time buckets \"year\", \"month\",\n\"week\" (ISO, Monday start). Lot/grower and pack date cannot be\naggregated. Empty values group under \"(none)\" — report its size when\nit matters (e.g. inspections with no region).\n\n`filters` maps field name → list. Server-filterable fields take ids\nfrom list_dimension_values (`{\"shipper\": [42]}`); colour takes names;\nother fields match values exactly, case-insensitive\n(`{\"label\": [\"Peelz\"]}`, `{\"flagged\": [true]}`).\n\n`tabs` (default approved) selects inspection status for non-buyers:\nunassigned, assigned, review-pending, approved, archived. Unassigned\nand assigned carry no score (counts only); review-pending scores are\nprovisional; archived means deleted. Buyers always see approved\ninspections for their own clients only, and cannot use region.\n\nComparing inspectors: group by inspector *within* commodity\n(`[\"commodity\", \"inspector\"]`), since inspectors grade different\nproduce; mention thin samples. Every rubric totals 100, so overall\nscores compare across commodities.\n\n`include_distribution`: adds percentiles and 10-point score bands per\ngroup (groups of 10+ only; at most 50 groups). Use for variability,\nconsistency and threshold questions.\n\n`include_examples`: adds up to 5 real inspections per group (2\nlowest, median, 2 highest) with id, score, PO and date — no extra\nupstream calls. Turn it on when the user asks which loads, why, what\nwent wrong, or about variability, or when a drill-down is likely;\nleave it off for pure rankings and trends. Examples are ids to drill\ninto with get_inspection_detail — never compute statistics from them.\n\nBuyers: filterable fields accept names or ids (e.g. `{\"shipper\":\n[\"The Fruitist\"]}`); a name that matches nothing or several values is\nrefused with the options. Buyers see approved inspections of their own\nclients, split by delivery date into received (delivered before today)\nand in-transit (today or later); both are always scanned, and arrival\n(today or tomorrow) is part of in-transit. Region and market group are\nnot available to buyers.\n\nAt most 200 groups (sorted by count; the rest merged into \"(other)\").\nGroupings with a time bucket sort chronologically and are refused\nrather than merged when over the cap. Read-only.",
  "inputSchema": {
    "type": "object",
    "required": [
      "date_from",
      "date_to",
      "date_basis",
      "group_by"
    ],
    "properties": {
      "tabs": {
        "anyOf": [
          {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          {
            "type": "null"
          }
        ],
        "default": null
      },
      "date_to": {
        "type": "string"
      },
      "filters": {
        "anyOf": [
          {
            "type": "object",
            "additionalProperties": {
              "type": "array",
              "items": {}
            }
          },
          {
            "type": "null"
          }
        ],
        "default": null
      },
      "group_by": {
        "type": "array",
        "items": {
          "type": "string"
        }
      },
      "date_from": {
        "type": "string"
      },
      "date_basis": {
        "enum": [
          "pickup",
          "delivery"
        ],
        "type": "string"
      },
      "include_examples": {
        "type": "boolean",
        "default": false
      },
      "include_distribution": {
        "type": "boolean",
        "default": false
      }
    },
    "additionalProperties": false
  }
}

Manufact

Server metadata

Discoverability

Protocol

Tools

MCP Apps

Tool documentation quality

Title56/100

Description97/100

Inputs0/100

Annotations0/100

Output schema0/100

Title67/100

Description99/100

Inputs0/100

Annotations0/100

Output schema0/100

Title55/100

Description90/100

Inputs100/100

Annotations0/100

Output schema0/100

Title51/100

Description99/100

Inputs0/100

Annotations0/100

Output schema0/100

Title57/100

Description100/100

Inputs0/100

Annotations0/100

Output schema0/100

Title48/100

Description94/100

Inputs0/100

Annotations0/100

Output schema0/100

Title44/100

Description83/100

Inputs100/100

Annotations0/100

Output schema0/100

Put your MCP to the test

Overview

Related MCP servers

FAQ

Not your MCP?

Server metadata

Discoverability

Protocol

Tools

MCP Apps

Tool documentation quality

Title56/100

Description97/100

Inputs0/100

Annotations0/100

Output schema0/100

Title67/100

Description99/100

Inputs0/100

Annotations0/100

Output schema0/100

Title55/100

Description90/100

Inputs100/100

Annotations0/100

Output schema0/100

Title51/100

Description99/100

Inputs0/100

Annotations0/100

Output schema0/100

Title57/100

Description100/100

Inputs0/100

Annotations0/100

Output schema0/100

Title48/100

Description94/100