The BLS MCP server provides access to U.S. Bureau of Labor Statistics data (employment, unemployment, wages, CPI, and more) through the following capabilities:
get_single_series – Fetch up to 3 years of historical data for any BLS series ID (e.g., CUUR0000SA0 for CPI)
get_latest_series – Retrieve only the most recent data point for a given series
get_multiple_series – Query 1–50 series simultaneously with optional year ranges and extras like calculations, annual averages, catalog info, and aspect data (most extras require an API key)
get_popular_series – List the 25 most popular BLS series, optionally filtered by survey type (e.g., CU for CPI, LA for Local Area Unemployment)
get_all_surveys – Browse all available BLS surveys with abbreviations and full names
get_survey – Get detailed metadata for a specific survey by its 2-letter abbreviation
Natural language support – A bundled Claude skill maps conversational queries (e.g., "What's the current CPI?") to the correct series IDs and tools
Access tiers:
Unregistered: 25 daily queries, up to 25 series per query, 10-year range
Registered (API key): 500 daily queries, up to 50 series per query, 20-year range, plus enhanced data options
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@BLS MCP What's the latest Consumer Price Index (CPI) data?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server that wraps the Bureau of Labor Statistics Public Data API v2, letting Claude query U.S. labor statistics — employment, unemployment, wages, CPI, and more — directly from a conversation.
Disclaimer: This project is an independent, unofficial tool and is not affiliated with, endorsed by, or associated with the U.S. Bureau of Labor Statistics, the U.S. Department of Labor, or any government agency. All data is fetched in real time from the publicly available
api.bls.govAPI. The accuracy, completeness, and timeliness of the data are the sole responsibility of that API. This tool is provided for informational and research purposes only. Nothing returned by this server constitutes legal, financial, economic, or policy advice. Use responsibly and in accordance with applicable laws.
API status: The BLS Public Data API is at v0.0.2-beta and subject to change without notice. Tool behaviour may change as the upstream API evolves.
Tool | Endpoint | Description |
|
| Retrieve data for a single time series for the past three years |
|
| Retrieve the most recent data point for a series |
|
| Retrieve data for one or more series with optional parameters |
|
| List the 25 most popular BLS series, optionally filtered by survey |
|
| List all BLS surveys with abbreviations and names |
|
| Retrieve metadata for a single BLS survey |
Related MCP server: BLS (Bureau of Labor Statistics) MCP Server
Parameter | Type | Description |
| string | BLS series ID (uppercase, digits, |
Parameter | Type | Required | Description |
| string[] | Yes | Array of BLS series IDs (1–50) |
| string | No | Start year in |
| string | No | End year in |
| boolean | No | Include catalog data (requires API key) |
| boolean | No | Include net/percent change calculations (requires API key) |
| boolean | No | Include annual averages (requires API key) |
| boolean | No | Include aspect data (requires API key) |
Parameter | Type | Required | Description |
| string | No | 2-letter survey abbreviation (e.g. |
Parameter | Type | Required | Description |
| string | Yes | 2-letter survey abbreviation (e.g. |
BLS series IDs may contain uppercase letters, digits, underscores (_), dashes (-), and hashes (#). Lowercase letters and other special characters are not accepted. Examples:
LAUCN040010000000005 — Local Area Unemployment
CUUR0000SA0 — Consumer Price Index
CES0000000001 — Current Employment Statistics
OEUN000000056--5747213213 — Occupational Employment
Use get_popular_series or get_all_surveys to discover valid series IDs and survey abbreviations.
The BLS API works without an API key, but with reduced limits:
Unregistered | Registered | |
Daily query limit | 25 | 500 |
Series per query | 25 | 50 |
Year range | 10 years | 20 years |
Optional parameters | No | catalog, calculations, annual averages, aspects |
Register for a free API key at https://data.bls.gov/registrationEngine/ and pass it via the BLS_API_KEY environment variable.
Node.js 18 or later
npm 9 or later
Claude Desktop (or any MCP-compatible client)
git clone https://github.com/larasrinath/bls_mcp.git
cd bls_mcp
npm install
npm run buildThe compiled server lands in ./dist/index.js.
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
Add the following block (adjust the path to match your machine):
{
"mcpServers": {
"bls": {
"command": "node",
"args": ["/absolute/path/to/bls_mcp/dist/index.js"],
"env": {
"BLS_API_KEY": "your-registration-key-here"
}
}
}
}The env block is optional — omit it to use the API without a key (lower rate limits apply).
macOS/Linux example:
"args": ["/Users/yourname/Projects/bls_mcp/dist/index.js"]Windows example:
"args": ["C:\\Users\\yourname\\Projects\\bls_mcp\\dist\\index.js"]Restart Claude Desktop after saving. The six BLS tools will appear in the tool picker.
This repo includes a Claude skill at skills/bls-query/ that teaches Claude how to map natural language queries (e.g. "What's the current CPI?") to the correct BLS series IDs and tools — without guessing.
The skill includes a series catalog covering CPI, unemployment, employment, JOLTS, PPI, wages, productivity, and more (~100 common series IDs).
To install for Claude Code: Copy the skills/bls-query folder into ~/.claude/skills/.
To install for Claude.ai: Upload the skills/bls-query folder via Settings > Capabilities > Skills.
What is the current unemployment rate? (use get_popular_series to find the series, then get_latest_series)
Show me CPI data for the last 3 years using series CUUR0000SA0.
Compare employment data for series CES0000000001 and CES3000000001 from 2020 to 2024.
What BLS surveys are available?
Tell me about the American Time Use survey.
What are the most popular Local Area Unemployment series?
# Run directly without building (uses tsx, included in devDependencies)
npm run dev
# Rebuild after changes
npm run buildbls_mcp/
├── src/
│ ├── index.ts # MCP server entry point
│ ├── client.ts # Typed BLS API client (axios)
│ └── tools/
│ ├── series.ts # get_single_series, get_latest_series, get_multiple_series
│ └── surveys.ts # get_popular_series, get_all_surveys, get_survey
├── skills/
│ └── bls-query/
│ ├── SKILL.md # Query workflow and tool selection guide
│ └── references/
│ └── series-catalog.md # ~100 common series ID mappings
├── package.json
├── tsconfig.json
├── LICENSE
└── README.mdThe BLS API enforces daily query limits (25 for unregistered, 500 for registered users). If you hit a rate limit, the server surfaces a clear error message rather than crashing silently. Register for a free API key to increase your limits.
MIT — see LICENSE.
Retrieve a list of all BLS surveys with their abbreviations and names.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description merely says 'retrieve', which is already implied by the verb. It adds no behavioral details such as authentication, read-only safety, or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that is front-loaded with the verb. Every word adds value with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple parameterless list retrieval, the description is largely adequate. However, it omits potential details like pagination or data scope, and the lack of an output schema leaves return format partially unspecified.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are zero parameters so the baseline is 4. The description adds meaning by specifying what is returned, compensating for the lack of parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves a list of all BLS surveys with abbreviations and names. It does not explicitly differentiate from sibling 'get_survey', but 'all' implies the scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like 'get_survey'. The description only states what it does, not when it is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve the most recent data point for a given BLS series ID.
| Name | Required | Description | Default |
|---|---|---|---|
| series_id | Yes | BLS series ID, e.g. LAUCN040010000000005 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description only mentions retrieving the most recent data point without details on limitations, caching, or error behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is concise and front-loaded with the core action, but could benefit from a bit more structure or formatting.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Minimal but adequate for a simple tool with one parameter and no output schema. Lacks explanation of return format or edge cases.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers the single parameter with description. Description adds no new meaning beyond what schema already provides; baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'retrieve' and resource 'most recent data point for a given BLS series ID', distinguishing it from siblings like get_single_series or get_multiple_series.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like get_single_series or get_survey. Missing context on prerequisites or scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve data for one or more BLS time series. Registered users can include up to 50 series IDs. Optionally specify start/end years (up to 20-year range), and enable catalog, calculations, annual averages, or aspects.
| Name | Required | Description | Default |
|---|---|---|---|
| series_ids | Yes | Array of BLS series IDs | |
| start_year | No | Start year in YYYY format | |
| end_year | No | End year in YYYY format | |
| catalog | No | Include catalog data (requires registration key) | |
| calculations | No | Include calculations such as net and percent changes (requires registration key) | |
| annual_average | No | Include annual average data (requires registration key) | |
| aspects | No | Include aspect data (requires registration key) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses key behaviors: 50-series limit for registered users, optional year range with 20-year constraint, and registration key requirements for catalog/calculations. No annotations exist, so this adds value beyond schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three short sentences, front-loaded with purpose, no unnecessary words. Every sentence adds essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Inputs are well described, but no output schema or description of return values. For a retrieval tool, missing what data is returned limits completeness for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Adds the 20-year range constraint on start/end years not present in schema, and summarizes boolean options. Schema already covers 100% of parameters, so baseline 3, but the added range detail earns a 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it retrieves data for one or more BLS time series, distinguishing from siblings like get_single_series by specifying 'one or more' and the 50-series limit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies usage for multiple series but does not explicitly guide when to choose this tool over alternatives like get_single_series or get_latest_series. No mention of when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve the 25 most popular BLS series IDs overall or for a specific survey. Optionally provide a survey abbreviation to filter by survey.
| Name | Required | Description | Default |
|---|---|---|---|
| survey | No | Optional 2-letter survey abbreviation, e.g. LA, CU, CE |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It reveals the tool returns 25 series IDs and can be filtered, but gives no details on rate limits, authentication, or data source. Adequate for a simple retrieval.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with key action and count, no unnecessary words. Efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (1 optional param, no output schema), the description fully covers purpose, scope, and filter option. No gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% coverage with description for survey parameter. The description adds 'filter by survey' which is already in the schema, so no new value beyond baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly specifies the action (retrieve), resource (popular BLS series IDs), count (25), and scope (overall or filtered by survey). It distinguishes from siblings like get_single_series, as it returns a list of popular series rather than a specific one.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description states the optional filter by survey, guiding when to use it. However, it does not explicitly mention when not to use this tool versus siblings like get_latest_series, though the context is implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve data for a single BLS time series for the past three years. Provide a valid BLS series ID (uppercase letters, numbers, underscores, dashes, hashes only).
| Name | Required | Description | Default |
|---|---|---|---|
| series_id | Yes | BLS series ID, e.g. LAUCN040010000000005 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses the data scope (past three years) but does not detail the output format, any rate limits, or potential side effects. For a read operation, this is adequate but lacks depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: two sentences, 16 words. It front-loads the purpose and immediately states the requirement. Every word earns its place, with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter tool with full schema coverage, the description is nearly complete. It covers what the tool does, the time range, and input format. However, since there is no output schema, the description could have mentioned the response structure to enhance completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers the parameter with 100% description, including an example. The description reinforces the valid character types (uppercase letters, numbers, underscores, etc.), adding value beyond the schema by clarifying the pattern.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves data for a single BLS time series, specifying a three-year time frame. It distinguishes from siblings like 'get_multiple_series' by explicitly saying 'single' and from 'get_latest_series' by implying a historical range.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description says to 'provide a valid BLS series ID' but does not offer explicit guidance on when to use this tool versus alternatives (e.g., when to use 'get_multiple_series' instead). The usage context is implied but not stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve metadata for a single BLS survey by its abbreviation.
| Name | Required | Description | Default |
|---|---|---|---|
| survey_abbreviation | Yes | Survey abbreviation, e.g. TU, CU, LA |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so description carries full burden. It describes a read operation without destructive effects, but lacks details on caching, rate limits, or data freshness. Adequate but minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded, no extraneous words. Every word contributes to understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists; description mentions 'metadata' but is vague about what fields are returned. A slightly more detailed description of typical metadata would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers 100% of parameters with examples. The description adds 'by its abbreviation' which reinforces schema but does not add new meaning beyond what schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action (retrieve metadata), the resource (single BLS survey), and the identifier (abbreviation). It distinguishes from sibling 'get_all_surveys' implicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description does not explicitly state when to use this tool versus alternatives like 'get_all_surveys'. Usage is implied but not clarified with exclusions or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0get_all_surveysget_latest_seriesget_multiple_seriesget_popular_seriesget_single_seriesget_surveyEach tool targets a distinct aspect of BLS data: surveys, single series, multiple series, latest, popular, and survey metadata. No overlap or ambiguity.
All tools follow a consistent 'get_' prefix with descriptive noun phrases (e.g., get_all_surveys, get_latest_series), making it easy to infer functionality.
With 6 tools, the set is well-scoped for a data retrieval API—neither too sparse nor overloaded.
Covers core operations: listing surveys, retrieving single/multiple series, popular series, and latest data. Missing search or filtering by year for single series, but overall quite complete.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Fetch US Bureau of Labor Statistics data — CPI, unemployment, wages, JOLTS, and more via MCP.
Macro data for AI agents: GDP, inflation, unemployment and more (World Bank, US BLS). No keys.
Macro data for AI agents: GDP, inflation, unemployment and more (World Bank, US BLS). No keys.
BLS MCP — Bureau of Labor Statistics public data API (v2)
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/larasrinath/bls_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server