--- canonical_url: "https://docs.composio.dev/toolkits/mospi_mcp" markdown_url: "https://docs.composio.dev/toolkits/mospi_mcp.md" product: "platform" version: null last_updated: null --- # MoSPI MCP India's official statistics from the Ministry of Statistics and Programme Implementation, queryable via natural language. - **Category:** analytics - **Auth:** NO_AUTH - **Composio-managed OAuth available?** N/A - **Tools:** 4 - **Triggers:** 0 - **Slug:** `MOSPI_MCP` - **Version:** 20260913_00 ## Tools ### Get data **Slug:** `MOSPI_MCP_GET_DATA` Fetches statistical data from a MoSPI dataset. This is the final step of the workflow. It requires filter values from get_metadata ΓÇö filter codes are arbitrary (e.g., indicator_code=3 means "Unemployment Rate" in PLFS but something different in other datasets). All filter parameters including limit and page go inside the filters dict, not as top-level arguments. Step 4 of: list_datasets ΓåÆ get_indicators ΓåÆ get_metadata ΓåÆ get_data #### Input Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `dataset` | string | Yes | Dataset name (PLFS, CPI, IIP, ISP, ASI, NAS, WPI, ENERGY, AISHE, ASUSE, GENDER, NFHS, ENVSTATS, RBI, NSS77, NSS78, NSS76, NSS75E, NSS79, CPIALRL, HCES, TUS, EC, UDISE, MNRE, NSS80, NSS73). CPI auto-routes to Group or Item endpoint based on whether filters contain item_code. IIP uses a single endpoint; pass frequency="Annually" or frequency="Monthly" in filters. | | `filters` | object | Yes | Key-value pairs from get_metadata filter_values. PLFS requires frequency_code (1=Annual, 2=Quarterly, 3=Monthly). NAS requires base_year ("2022-23" or "2011-12"). MNRE: indicator_code (1-5) is mapped to type_of_renewable_energy_code. Pass limit (e.g., "50") to retrieve more than 10 records. | ### Get indicators **Slug:** `MOSPI_MCP_GET_INDICATORS` Returns the full list of available indicators for a given dataset. Datasets often have broader coverage than expected ΓÇö for example, ASI covers 57 indicators (capital structure, wages, employment, GVA, fuel consumption), and GENDER covers 147 indicators across health, education, labor, and crime. For PLFS and ASUSE, indicators are grouped by frequency_code: - PLFS frequency_code=1 (Annual): all 8 indicators including wages - PLFS frequency_code=2 (Quarterly): indicators 1-3 only - PLFS frequency_code=3 (Monthly): indicators 1-3 only frequency_code selects the indicator set, not time granularity. Step 2 of: list_datasets ΓåÆ get_indicators ΓåÆ get_metadata ΓåÆ get_data #### Input Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `level` | string | No | | | `Format` | string | No | | | `series` | string | No | | | `dataset` | string | Yes | Dataset name ΓÇö one of: PLFS, CPI, IIP, ISP, ASI, NAS, WPI, ENERGY, AISHE, ASUSE, GENDER, NFHS, ENVSTATS, RBI, NSS77, NSS78, NSS76, NSS75E, NSS79, CPIALRL, HCES, TUS, EC, UDISE, MNRE, NSS80, NSS73. For CPI, IIP, ISP, WPI: returns available base years and frequencies. | | `base_year` | string | No | | | `frequency` | string | No | | | `user_query` | string | No | The user's original question. Captured for telemetry analytics; not echoed back in the response. | | `frequency_code` | string | No | | | `classification_year` | string | No | | ### Get metadata **Slug:** `MOSPI_MCP_GET_METADATA` Returns the valid filter values (states, years, quarters, etc.) for a given dataset and indicator. Filter codes are arbitrary and dataset-specific ΓÇö for example, PLFS state_code 99 means "All India", and NAS frequency_code 1 means "Annual". These values cannot be inferred or guessed from parameter names alone. The returned filter_values and api_params should be used as-is when calling get_data. Step 3 of: list_datasets ΓåÆ get_indicators ΓåÆ get_metadata ΓåÆ get_data #### Input Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `type` | string | No | | | `level` | string | No | Required for CPI ("Group"/"Item"). | | `Format` | string | No | | | `module` | string | No | For NSS77 only ΓÇö land_livestock (portal nss77) or aidis (portal nss77a). Required when indicator_code overlaps both modules (16-19, 24, 26, 29, 32, 34, 36). Auto-derived for codes unique to one module. | | `series` | string | No | For CPI and NAS only ("Current"/"Back"). | | `dataset` | string | Yes | Dataset name (same values as get_indicators). | | `base_year` | string | No | Required for CPI ("2024"/"2012"/"2010"), IIP ("2011-12"/"2004-05"/"1993-94"), NAS ("2022-23"/"2011-12"), WPI ("2011-12"/"2004-05"/"1993-94"). Not applicable for PLFS, ASI. | | `frequency` | string | No | Required for IIP ("Annually"/"Monthly"). | | `state_code` | string | No | For NAS only — required when indicator_code is 23-34 (state-level GSDP/NSDP/GSVA family). Values 01-37, where 37 = All-India aggregate. Comma separated for multiple states. Not applicable when frequency_code=2 (Quarterly) — state-level indicators have Annual data only. | | `survey_code` | string | No | For NSS76 (1=Disability, 2=Housing & drinking water), NSS75E (2=Education, indicators 43-55), NSS80 (1=Telecom (CMST), 2=Education (CMSE)), and NSS77 AIDIS module (always 1). | | `frequency_code` | string | No | Required for PLFS and ASUSE. PLFS: 1=Annual, 2=Quarterly bulletin, 3=Monthly. ASUSE: 1=Annual, 2=Quarterly. | | `indicator_code` | string | No | Required for: PLFS, NAS, ENERGY, AISHE, ASUSE, GENDER, NFHS, ENVSTATS, RBI, NSS77, NSS78, NSS76, NSS75E, NSS79, CPIALRL, HCES, TUS, EC, UDISE, MNRE, NSS80, NSS73. Not applicable for: CPI, IIP, ISP, ASI, WPI. For RBI, this maps to sub_indicator_code internally. | | `sub_indicator_code` | string | No | | | `classification_year` | string | No | Required for ASI ("2008"/"2004"/"1998"/"1987"). | | `use_of_energy_balance_code` | string | No | For ENERGY only (1=Supply, 2=Consumption). | ### List datasets **Slug:** `MOSPI_MCP_LIST_DATASETS` Returns an overview of all MoSPI statistical datasets with descriptions and coverage. This is the starting point ΓÇö call this first to identify the right dataset. The API covers 500+ indicators across employment, prices, industry, national accounts, health, education, disability, housing, environment, trade, and more. Each dataset has its own indicator codes, filter parameters, and valid values ΓÇö these are not standardized and cannot be inferred or guessed from parameter names alone. Four-step workflow (each step depends on the previous): 1. list_datasets() ΓÇö identify the dataset 2. get_indicators(dataset) ΓÇö list available indicators 3. get_metadata(dataset, indicator_code) ΓÇö retrieve valid filter values 4. get_data(dataset, filters) ΓÇö fetch the data Returns: dict with 'datasets' (name, description, use_for for each dataset) and 'workflow' (the four-step sequence).