This server lets you discover, query, and analyze Thailand's official statistics from the National Statistical Office (NSO) via the SDMX REST API using natural language.
Discover Dataflows: Search ~900 TNSO datasets by keyword (Thai or English) or by required dimension codes to find relevant dataflows.
Get Data Structure: Retrieve the full DSD for any dataset — ordered dimensions and their associated codelists.
Get Constraints: Fetch all valid dimension values (with Thai/English labels) and the available time range for a dataflow. Time periods use Buddhist Era (BE = Gregorian + 543, e.g. 2024 → 2567).
Get Codelist Descriptions: Retrieve Thai and English labels for every code in a given codelist (e.g., province codes, sex codes).
Resolve Concepts: Look up a TNSO SDMX concept ID to get its Thai or English name.
Fetch Data: Query statistical observations as a TSV table with dimension filtering and Buddhist Era time ranges. Includes self-diagnosis of empty results with suggested valid alternatives.
Check Data Availability: Pre-flight check to verify a filter/period combination will return results before a full fetch.
Look Up Territorial Codes: Find official Thai geography codes for regions, provinces (77 changwat), or districts by Thai or English name — essential before filtering by geography.
Cache Diagnostics: Inspect the on-disk cache health and contents for troubleshooting.
Typical workflow:
Use discover_dataflows to find a relevant dataset.
Use get_constraints to understand valid filter values and time ranges.
Optionally use get_territorial_codes to find province/region codes.
Use get_data to fetch the actual observations.
Click on "Deploy 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., "@Thailand NSO MCP Server Find aging index data for Thailand"
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.
Research repository — not for data access.
aard-ai/tnso-mcp-server is a research artefact, built for studying how MCP servers behave against
different statistical agencies' SDMX endpoints. It is not maintained, is not published to
any package registry, and must not be used as an MCP server for data access.
An MCP server that lets an LLM discover, query and
analyse Thailand's official statistics from the National Statistical Office (NSO,
agency TNSO) via the SDMX REST API — in natural language.
This is a lightweight MCP that uses keyword search (this is not the Aard MCP).
It should be effective for e.g. searching for indicators or dataflows.
Note that this lightweight approach is much less effective for certain question types such as "Compare Bangkok and Chon buri", or "Tell me about trade of all fish that are not tuna". These kinds of questions benefit from structure-based search across all data sources, just two factors that make the Aard MCP different from other tools.
When connected to your chat tool (e.g. Gemini or Claude) it can generate analysis like the below:
This implementation based on a port of ondata/istat_mcp_server
(Italy / ISTAT), adjusted to point to the Thaliand NSO SDMX endpoint at
https://ns1-stathub.nso.go.th/rest.
It uses a 9-tool workflow (like the ISTAT MCP), same two-layer caching; the data source, agency, languages (Thai/English) and geography (Thai provinces) are swapped in.
Note we use Buddhist Era dates. TNSO publishes time periods in the Buddhist Era calendar (BE = Gregorian + 543). So
2567means 2024. Passstart_period/end_periodas BE years.
Tool | What it does |
| Search ~900 TNSO dataflows by keyword (Thai/English; any keyword matches (OR), or |
| Dimensions + codelists for a data structure (DSD). |
| Valid values (with labels) per dimension + available time range. Start here. |
| Thai/English labels for every code in a codelist. |
| Resolve an SDMX concept id to its Thai/English name. |
| Fetch observations as a TSV table (+ reproducible CSV/curl URLs). On an empty result it self-diagnoses (invalid codes / out-of-range period) and suggests verified non-empty alternatives. |
| Pre-flight check that a specific filter/period combination returns rows before a full |
| Thai geography codes: region ( |
| Inspect the on-disk cache. |
Typical workflow: discover_dataflows → get_constraints → get_data
(use get_territorial_codes first when you need province/region codes). get_data
self-diagnoses empty results and suggests working alternatives; use
check_data_availability to pre-check a combination before fetching.
Related MCP server: mcp-uk-ons
Requires Python ≥ 3.11. Using uv (recommended):
git clone https://github.com/aard-ai/tnso-mcp-server.git
cd tnso-mcp-server
uv venv
uv pip install -e ".[dev]"
# Run the server (stdio transport)
uv run python -m tnso_mcp_serverOr with pip:
cd tnso-mcp-server
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
python -m tnso_mcp_serverClaude Code:
claude mcp add tnso -- uv --directory /abs/path/to/tnso-mcp-server run python -m tnso_mcp_serverClaude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"tnso": {
"command": "uv",
"args": ["--directory", "/abs/path/to/tnso-mcp-server", "run", "python", "-m", "tnso_mcp_server"]
}
}
}Copy .env.example to .env to override defaults (API base URL, timeouts, cache TTLs,
log level, dataflow blacklist). All values have sensible defaults, so .env is optional.
discover_dataflows(keywords="aging")
-> DF_01DI_IND_AGING — "Aging Index dataflow"
discover_dataflows(covers={"CWT": ["10", "20"]})
-> every dataflow whose data covers both Bangkok (10) and Chon Buri (20)
get_constraints(dataflow_id="DF_01DI_IND_AGING")
-> dimensions POP_IND, SEX, AREA, CWT, ...; TIME_PERIOD range 2557–2567 (BE)
get_territorial_codes(level="province", name="bangkok")
-> { code: "10", name_en: "Krung Thep Maha Nakhon (Bangkok)", name_th: "กรุงเทพมหานคร" }
get_data(dataflow_id="DF_01DI_IND_AGING", dimension_filters={"CWT": ["10"]}, start_period="2560", end_period="2567")
-> TSV table of the aging index for Bangkok, 2017–2024uv run pytest -m "not integration" # fast unit tests (no network)
uv run pytest -m integration # live tests against the real TNSO API
uv run pytest # everythingMIT (same as the upstream istat_mcp_server).
Discover available TNSO (Thailand National Statistical Office) dataflows. Optionally filter by comma-separated keywords (matched against id, Thai/English name and description). Start here to find a dataset, then call get_constraints.
| Name | Required | Description | Default |
|---|---|---|---|
| keywords | No | Comma-separated keywords, e.g. 'population, aging' or 'labour'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so description carries full burden. It mentions discover and optional filtering but does not disclose whether the tool is read-only, has side effects, or any rate limits. While a discovery tool is likely safe, the omission leaves ambiguity.
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?
Two concise sentences front-load the purpose and action, with zero redundancy. Every word earns its place.
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?
With one optional parameter and no output schema, the description is mostly complete. It covers purpose, filtering behavior, and next step. However, it could explicitly state the return format (e.g., 'returns a list of dataflows with id, name, description') for full clarity.
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 coverage is 100%, baseline 3. The description adds value by explaining that keywords match against id, Thai/English name, and description—information not in the schema, which only gives examples.
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 it discovers TNSO dataflows with specific verb 'discover' and resource 'dataflows'. It further distinguishes itself from siblings by advising to 'start here' and then call get_constraints, showing unique positioning.
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?
Provides explicit when-to-use guidance ('Start here to find a dataset') and next-step instruction ('then call get_constraints'), effectively differentiating from sibling tools without saying 'not for'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check persistent-cache health (exists, size, writability). Pass debug=true to additionally reveal the cache path and stored keys (host-sensitive). For debugging.
| Name | Required | Description | Default |
|---|---|---|---|
| debug | No | Include the host cache path and cached keys (default false). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that debug mode reveals host-sensitive info (cache path and keys), and the default mode checks health without sensitivity. This is good transparency for a diagnostic tool.
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 consists of two concise sentences that front-load the primary purpose and then add the debug detail. There is no redundant information, and 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?
Given the tool's simplicity (one parameter, no output schema), the description is adequate but could be more complete. It does not specify what the output looks like or provide more detailed usage scenarios beyond 'debugging'. A score of 3 reflects this gap.
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 schema description covers the debug parameter fully, but the tool description adds the 'host-sensitive' warning, which provides valuable semantic context beyond the schema. This justifies a score above the baseline of 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 'Check' and the resource 'persistent-cache health' with specific attributes (exists, size, writability). It distinguishes the tool from siblings like discover_dataflows and get_concepts, which focus on different data aspects.
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 implies usage for debugging cache issues with 'For debugging.' but does not provide explicit when-not-to-use scenarios or alternatives. However, siblings do not overlap directly, so ambiguity is minimal.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get Thai and English labels for every code in a codelist (e.g. 'CL_CWT').
| Name | Required | Description | Default |
|---|---|---|---|
| codelist_id | Yes | Codelist id, e.g. 'CL_SEX'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description indicates a read operation ("Get") with no side effects, which is appropriate. It does not contradict any annotations (none provided). However, it lacks details on response format or behavior for invalid input.
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 verb and resource, no unnecessary words.
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 tool with one parameter and no output schema, the description is mostly complete. It explains the resource and provides an example. Minor gap: does not specify whether the response includes codes or just labels, but the context is adequate.
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 coverage is 100% with a clear parameter description. The tool description adds an example but no additional semantic meaning beyond what the schema 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?
The description clearly states the tool gets labels for every code in a codelist, with an example. It distinguishes from sibling tools like get_structure or get_concepts which serve different purposes.
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?
While the description implies usage for retrieving code labels, it does not explicitly state when to use or not use this tool, nor does it mention alternatives. No guidance on prerequisites or error conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Resolve a TNSO SDMX concept id to its Thai or English name (searches all TNSO concept schemes; result cached). Use lang='th' or lang='en'.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | en | |
| concept_id | Yes | Concept id, e.g. 'POP_IND'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must carry the full burden. It discloses caching behavior and that it searches all TNSO concept schemes. Missing details like error handling, return format, or what happens if concept_id is not found, but the core behavior is clear.
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?
Two sentences that efficiently convey purpose, scope, and a usage hint. No unnecessary words, and the key information is front-loaded.
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?
The tool has no output schema, and the description implies the return is the resolved name. For a simple lookup, this is fairly complete, but mentioning the return type (string) or possible error responses 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?
The schema describes concept_id with an example but lacks description for lang. The description adds 'Use lang='th' or lang='en'.', which clarifies the lang parameter's enum values and usage. This adds value beyond the schema, especially for the undocumented lang parameter.
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's purpose: resolving a TNSO SDMX concept id to its Thai or English name. It specifies the scope (all TNSO concept schemes) and distinguishes from sibling tools like get_codelist_description, which deals with codelists.
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 provides clear context on when to use the tool (for concept resolution) and includes a usage hint for the language parameter. However, it does not explicitly state when not to use this tool or mention alternatives among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get all valid dimension values (with Thai/English labels) and the available time range for a dataflow. One call returns everything needed to build a get_data query. Time periods are Buddhist Era (BE = Gregorian + 543).
| Name | Required | Description | Default |
|---|---|---|---|
| dataflow_id | Yes | Dataflow id, e.g. 'DF_01DI_IND_AGING'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears the full burden. It discloses that it returns dimension values with Thai/English labels, time range, and explains the Buddhist Era conversion. It could mention whether the operation is read-only or idempotent, but overall good disclosure.
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?
Two sentences that are front-loaded and concise: first states what it does, second adds usage guidance and a conversion note. No wasted words.
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 no output schema, the description adequately explains the return value (dimension values, labels, time range) and provides a conversion note. It does not detail the output structure but is sufficient for an agent to understand its purpose. Slight improvement could be made by hinting at the output format.
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 coverage is 100% with a parameter description and example. The description adds context about the output but does not further explain the dataflow_id parameter beyond what the schema provides. Baseline 3 is appropriate.
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 gets 'all valid dimension values (with Thai/English labels) and the available time range for a dataflow', specifying verb and resource. It distinguishes from siblings like get_data (which retrieves actual data) and discover_dataflows (which lists dataflows).
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 indicates this tool is used to retrieve constraints needed to build a get_data query, providing clear context. However, it does not explicitly state when not to use it or mention alternatives, though the context is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch observations for a dataflow as a TSV table, with reproducible CSV/curl URLs. Supports dimension filtering and a time range. Omit dimensions from dimension_filters to get all their values; pass multiple codes per dimension as an array. If no period is given, the latest available year is returned. IMPORTANT: start_period/end_period are Buddhist Era years (e.g. 2567 = 2024).
| Name | Required | Description | Default |
|---|---|---|---|
| detail | No | full | |
| end_period | No | Buddhist-era end, e.g. '2567'. | |
| dataflow_id | Yes | Dataflow id, e.g. 'DF_01DI_IND_AGING'. | |
| start_period | No | Buddhist-era start, e.g. '2560'. | |
| dimension_filters | No | Map of dimension id -> array of codes, e.g. {"CWT": ["10"], "SEX": ["_T"]}. May also be that object JSON-encoded as a string. | |
| dimension_at_observation | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full behavioral disclosure burden. It explains the output format and the effect of omitting periods/dimensions, but lacks details on error handling, permissions, rate limits, or the structure of the returned TSV/URLs. The disclosure is adequate but not comprehensive.
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 relatively concise with three sentences that front-load the main purpose. It uses clear structure and avoids redundancy, though a minor improvement could be to separate usage notes more clearly.
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 complexity (6 parameters, nested objects, no output schema), the description covers key behaviors but omits details about the detail parameter, dimension_at_observation, and how the reproducible URLs are structured. It is sufficient but not fully comprehensive.
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 description coverage is 67%, so baseline is 3. The description adds value by clarifying that dimension_filters can be a string (JSON-encoded), the effect of omitting dimensions, and the Buddhist Era year format. This goes beyond the schema's descriptions.
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 'fetch', the resource 'observations for a dataflow', and the output format 'TSV table'. It also mentions reproducible URLs, making the tool's purpose specific and distinguishable from sibling tools like discover_dataflows or get_structure.
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 provides explicit usage guidance: how to omit dimensions, pass multiple codes, and the default period behavior. It includes an important note about Buddhist Era years. However, it does not explicitly state when to avoid using this tool or suggest alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the data structure (DSD) for a datastructure id: the ordered list of dimensions and the codelist each uses. Fast path when you already know the codes.
| Name | Required | Description | Default |
|---|---|---|---|
| datastructure_id | Yes | DSD id, e.g. 'DSD_01DI_IND_AGING'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It mentions 'fast path' but fails to detail authentication, side effects, rate limits, or return format, leaving significant gaps.
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 two sentences, front-loading the core purpose and immediately adding usage context. Every phrase earns its place without 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?
Given the tool's simplicity and lack of output schema, the description covers the basic return value (dimensions and codelists) but omits details on error cases, pagination, or data format, leaving it adequate but not thorough.
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 coverage is 100% for the single parameter, so the description adds minimal extra meaning beyond the schema's example. The 'fast path' hint provides context but not parameter-specific semantics.
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 gets the data structure (DSD) for a given ID, specifying it returns ordered dimensions and codelists. This distinguishes it from siblings like get_codelist_description or get_data.
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 phrase 'Fast path when you already know the codes' implies a specific usage scenario, but it does not explicitly state when not to use the tool or mention alternatives like discover_dataflows for exploring structures.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Look up Thai geography codes used by the AREA / CWT dimensions: level='region' (CL_AREA), 'province' (CL_CWT, 77 changwat), or 'district' (CL_AMPHOE). Filter by 'name' (Thai or English substring). Use this to find codes before calling get_data.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Place-name substring (Thai or English). | |
| level | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It explains the level mapping and substring filtering behavior, but does not disclose the return format, case-sensitivity, limits, or error handling. This is adequate but incomplete for a lookup tool.
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?
Two succinct sentences with no wasted words. The purpose is front-loaded, and the essential details (levels, filtering, usage hint) are efficiently conveyed.
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?
Despite being a simple tool with 2 optional parameters and no output schema, the description omits the return structure. It states 'look up...codes' but does not explain if results are a list, map, or include additional metadata. For a lookup tool, this is a notable gap in 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 coverage is 50% (name described, level not). The description adds significant meaning to the level parameter by mapping each enum value to a code list identifier (CL_AREA, CL_CWT, CL_AMPHOE) and providing context (77 changwat). It reinforces the name parameter as accepting Thai or English substrings, adding value beyond the schema.
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 looks up Thai geography codes used by specific dimensions (AREA/CWT) and lists three levels with their code list identifiers. This provides a specific verb-resource pair and distinguishes it from sibling tools like get_data or get_codelist_description.
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 explicitly advises to use this tool before calling get_data, providing direct guidance on when to invoke it. However, it does not mention any when-not-to-use scenarios or alternatives among siblings.
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.
v0.1.0discover_dataflowsget_cache_diagnosticsget_codelist_descriptionget_conceptsget_constraintsget_dataget_structureget_territorial_codesScored across 8 tools
Each tool has a distinct purpose: discovery, structure, constraints, data retrieval, code lookups, and diagnostics. No overlap exists; even get_codelist_description and get_constraints serve different needs.
All tool names follow a consistent verb_noun pattern with snake_case (e.g., discover_dataflows, get_constraints, get_data), making it predictable for agents.
With 8 tools, the set is well-scoped for a statistical data server, covering discovery, structure, query building, data retrieval, and code lookups without unnecessary tools.
The tool surface covers the full workflow: discover dataflows, get structure and constraints, fetch data, and resolve codes. No obvious gaps for a public statistics API.
Search and query 1,500+ OECD statistical datasets via SDMX. Keyless.
Query IMF SDMX 3.0 macroeconomic dataflows — WEO, BOP, CPI, exchange rates, 190 countries.
政府統計 (e-Stat) の API を通じて、統計データやメタ情報を取得するためのサービスです。
Query official statistics of Catalonia (Idescat): tables, metadata and JSON-stat data via MCP.
