ask_pipeworx_grounded
Exposed by 1312 servers, with 3 different definitions behind the one name.
The same name does not mean the same tool here.
1312 servers expose ask_pipeworx_grounded and we have recorded 3 distinct definitions of it. Compare the parameters below before assuming one is a drop-in for another.
DataDetroit MCP — Detroit open data (data.detroitmi.gov, ArcGIS REST API).
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
France Economy & Finance Open Data (data.economie.gouv.fr) — OpenDataSoft MCP.
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
DataEdmonton MCP — Edmonton open data (data.edmonton.ca, Socrata SODA API).
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
ENERGY STAR Open Data (data.energystar.gov) Socrata MCP.
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
data.europa.eu — official EU open-data hub (~1.6M datasets)
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
FCC Open Data (opendata.fcc.gov) Socrata MCP.
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
Fort Worth Open Data (data.fortworthtexas.gov) Socrata MCP.
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
Fulton County Open Data (sharefulton.fultoncountyga.gov) Socrata MCP.
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
France data.gouv.fr open-data catalogue
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
Data.gov MCP — wraps Data.gov CKAN API (catalog.data.gov/api/3)
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
Australia data.gov.au open-data catalogue (CKAN)
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
data.gov.ie MCP — Ireland's national open-data portal (CKAN API).
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
data.gov.il MCP — Israel national open-data portal (CKAN API).
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
India Open Government Data (OGD) Platform MCP — data.gov.in
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
data.gov.sg MCP — Singapore open data + real-time environment/transport feeds
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
data.govt.nz CKAN MCP.
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
data.gov.uk MCP — UK national open-data portal (CKAN API).
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
Greece Open Data (data.gov.gr) CKAN MCP.
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
Howard County Open Data (opendata.howardcountymd.gov) Socrata MCP.
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
Île-de-France Open Data (data.iledefrance.fr) — OpenDataSoft MCP.
Ask Pipeworx — Grounded
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,635 across 1477 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.
| Parameter | Type | Description |
|---|---|---|
| q | string | Alias for question. |
| text | string | Alias for question. |
| input | string | Alias for question. |
| query | string | Alias for question. |
| prompt | string | Alias for question. |
| question* | string | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
* required
Author's annotations: readOnlyHint=True, openWorldHint=True, idempotentHint=True, destructiveHint=False. These are claims by whoever wrote the server, not something we verified.
What this page is
Every field above is reproduced as the server published it at the time shown. The description and the annotations are claims by the server's author. Toolpin does not call tools, so we cannot tell you whether a tool does what it says.
What we can tell you is whether the claim changed. The hash covers the fields the MCP specification defines, so a vendor build stamp does not move it but a rewritten description does. See how we monitor, or this server's change history.