ko-mcp

get_economic_indicators

Read-onlyIdempotent

Get U.S. economic indicators from BLS — CPI (inflation), PPI (producer prices), Non-farm Payrolls (employment), Unemployment Rate, JOLTS. Filter by category.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`days`	No	Number of days of history (default 365)
`page`	No	Page number (default 1)
`limit`	No	Rows per page, 1-500 (default 100). A long `days` window can hold more rows than one page; the answer says when the page is full and names the next one.
`category`	No	Category (case-insensitive): cpi/inflation, ppi, nfp/payrolls, unemployment, jolts, or all	all

Output Schema

TableJSON Schema

Name	Required	Description
`rows`	Yes
`paging`	Yes	Paging state reconciled from ko.io meta.total_count and meta.softwall
`category`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 26, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "category": {
+      "type": "string"
+    },
+    "paging": {
+      "additionalProperties": false,
+      "description": "Paging state reconciled from ko.io meta.total_count and meta.softwall",
+      "properties": {
+        "continuation": {
+          "description": "SIGNIN_REQUIRED = page>1 needs a (free) ko.io API key",
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "has_more": {
+          "description": "null = a full page came back and more MAY exist",
+          "type": [
+            "boolean",
+            "null"
+          ]
+        },
+        "next_page": {
+          "anyOf": [
+            {
+              "$ref": "#/properties/paging/properties/total_count/anyOf/0"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "description": "Next page THIS caller can open; null when there is none (or sign-in is required)"
+        },
+        "page": {
+          "type": "integer"
+        },
+        "per_page": {
+          "type": "integer"
+        },
+        "plan_row_cap": {
+          "anyOf": [
+            {
+              "$ref": "#/properties/paging/properties/total_count/anyOf/0"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "description": "Row cap the caller's plan applied to this page, if any"
+        },
+        "returned": {
+          "type": "integer"
+        },
+        "total_count": {
+          "anyOf": [
+            {
+              "type": "integer"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "description": "Total rows matching the request, when ko.io reported it"
+        },
+        "truncated_by_plan": {
+          "description": "True when the plan's row cap withheld rows from this page",
+          "type": "boolean"
+        }
+      },
+      "required": [
+        "page",
+        "per_page",
+        "returned",
+        "total_count",
+        "has_more",
+        "next_page",
+        "continuation",
+        "plan_row_cap",
+        "truncated_by_plan"
+      ],
+      "type": "object"
+    },
+    "rows": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "category": {
+            "$ref": "#/properties/rows/items/properties/date"
+          },
+          "date": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "series_id": {
+            "$ref": "#/properties/rows/items/properties/date"
+          },
+          "series_name": {
+            "$ref": "#/properties/rows/items/properties/date"
+          },
+          "value": {
+            "anyOf": [
+              {
+                "pattern": "^-?\\d+(\\.\\d+)?([eE][-+]?\\d+)?$",
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Exact decimal string as served by ko.io (not rounded); null = unknown"
+          }
+        },
+        "required": [
+          "date",
+          "series_id",
+          "series_name",
+          "value",
+          "category"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "category",
+    "rows",
+    "paging"
+  ],
+  "type": "object"
+}

Changed2 schema fields changedSep 12, 2026

addedInput schema / properties / limit

Added value: +{
+  "default": 100,
+  "description": "Rows per page, 1-500 (default 100). A long `days` window can hold more rows than one page; the answer says when the page is full and names the next one.",
+  "maximum": 500,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / page

Added value: +{
+  "default": 1,
+  "description": "Page number (default 1)",
+  "minimum": 1,
+  "type": "integer"
+}

First observedJul 11, 2026

TDQS

A4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety and side effects. The description adds no behavioral details beyond the data source and categories; it doesn't mention pagination, rate limits, or response format. Since annotations carry the burden, a score of 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, well-structured sentence that front-loads the core purpose and lists all relevant indicators. There is no wasted wording, and the filtering note is appropriately included.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is straightforward, has an output schema, and annotations cover safety. The description states the data source and categories, which is enough for an agent to know what it does. Pagination is documented in the schema, so the description needn't repeat it. It could mention that it returns historical time series, but the days parameter implies that. Slightly above minimum but not exhaustive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% – every parameter has a description in the input schema. The description's 'Filter by category' simply echoes the category parameter. No new meaning is added beyond what the schema already provides, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Get U.S. economic indicators from BLS' and enumerates the specific indicators (CPI, PPI, NFP, Unemployment, JOLTS). It also notes the filtering capability. This is a specific verb+resource and distinguishes it from sibling tools that cover different domains (congress, crypto, fed rates, etc.).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies its usage by naming the data source and indicators, and the sibling tools are clearly for other data types. However, it doesn't explicitly state when to use this tool versus alternatives or any exclusions. Given the clear domain separation, this is acceptable but not fully explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All ko-mcp tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.