Toolpin

Tool index

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.

io.github.pipeworx-io/data-baltimore reachable

DataBaltimore MCP — Baltimore open data (data.baltimorecity.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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
io.github.pipeworx-io/data-batonrouge reachable

Baton Rouge Open Data (data.brla.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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
io.github.pipeworx-io/data-bloomington reachable

Bloomington Open Data (data.bloomington.in.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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
io.github.pipeworx-io/data-boston reachable

DataBoston MCP — City of Boston open data (data.boston.gov, 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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
io.github.pipeworx-io/data-brussels reachable

Brussels Open Data (opendata.bruxelles.be) — 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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
io.github.pipeworx-io/data-calgary reachable

DataCalgary MCP — Calgary open data (data.calgary.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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
io.github.pipeworx-io/data-cambridge reachable

DataCambridge MCP — Cambridge open data (data.cambridgema.gov, 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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
io.github.pipeworx-io/data-centrevaldeloire reachable

Centre-Val de Loire Open Data (data.centrevaldeloire.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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
io.github.pipeworx-io/data-cincinnati reachable

DataCincinnati MCP — Cincinnati open data (data.cincinnati-oh.gov, 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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
io.github.pipeworx-io/datacite reachable

DataCite MCP — DOIs for research datasets (free, no auth)

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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
io.github.pipeworx-io/data-cityofchicago reachable

City of Chicago Socrata open-data portal

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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
io.github.pipeworx-io/data-cityofnewyork reachable

NYC open data via Socrata SoQL — 311, transport, housing, permits, crime, health.

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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
io.github.pipeworx-io/data-colorado reachable

Colorado open data via Socrata SoQL — business, government, health, demographics.

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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
io.github.pipeworx-io/data-connecticut reachable

Connecticut open data via Socrata SoQL — agencies, public health, education, transport.

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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
io.github.pipeworx-io/data-cookcounty reachable

Cook County Open Data (datacatalog.cookcountyil.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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
io.github.pipeworx-io/datacube-sk reachable

DATAcube — Statistical Office of the Slovak Republic (data.statistics.sk).

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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
io.github.pipeworx-io/data-dallas reachable

DataDallas MCP — Dallas open data (www.dallasopendata.com, 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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
io.github.pipeworx-io/data-dc reachable

DataDC MCP — Washington, DC open data (opendata.dc.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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
io.github.pipeworx-io/data-delaware reachable

Delaware Open Data (data.delaware.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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
io.github.pipeworx-io/data-denver reachable

DataDenver MCP — Denver open data (opendata-geospatialdenver.hub.arcgis.com, 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.

ParameterTypeDescription
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.

no output schema sha256 64dc6854f07d8062 read 2026-08-27 repository
← previous more servers →

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.