このMCPでできること
Discovers maintained data capabilities, processes and audits bounded CSV files, and securely shares or revokes access to stored agent results.
機能
ツール
10
ツール
create_result_reference
Authorize one recipient client_id to read one owned result with its own credential. Returns a credential-free, expiring reference for agent handoff. Owner access stays in the configured header. Requires explicit intended recipient; no permission to other jobs, deletion or resharing.
入力スキーマ
{'type': 'object', 'required': ['recipient_client_id', 'job_id', 'request_key'], 'properties': {'job_id': {'type': 'string', 'pattern': '^job_[a-f0-9]{32}$'}, 'request_key': {'type': 'string', 'pattern': '^[A-Za-z0-9][A-Za-z0-9_.-]{0,79}$', 'description': 'Stable reference idempotency key. Reuse with identical job, recipient and requested lifetime.'}, 'ttl_seconds': {'type': 'integer', 'default': 900, 'maximum': 3600, 'minimum': 1, 'description': "Reference lifetime, also bounded by the job and both access credentials' expiry."}, 'recipient_client_id': {'type': 'string', 'pattern': '^client_[a-f0-9]{24}$', 'description': 'Public client identifier provided by the intended recipient through an authorized connection. Never their token.'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object'}
delete_job
Delete the owner's stored result content. Retains an idempotency tombstone until expiry and does not reset quotas. Configure the owner's bearer access header.
破壊的操作あり
入力スキーマ
{'type': 'object', 'required': ['job_id'], 'properties': {'job_id': {'type': 'string', 'pattern': '^job_[a-f0-9]{32}$'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object'}
get_catalog
Read public capabilities, free allowances, access bootstrap, privacy, retention and HTTP discovery routes. No access credential required.
読み取り専用
入力スキーマ
{'type': 'object', 'properties': {}, 'additionalProperties': False}
出力スキーマ
{'type': 'object'}
get_job
Recover the original complete private CSV or audit result using its job_id and the owner's bearer access header. Results expire within 24 hours and cannot outlive access.
読み取り専用
入力スキーマ
{'type': 'object', 'required': ['job_id'], 'properties': {'job_id': {'type': 'string', 'pattern': '^job_[a-f0-9]{32}$'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object'}
get_result_reference
Retrieve the full shared result using the nominated recipient's configured bearer header. The reference alone grants no access. Expired, revoked or deleted results are unavailable.
読み取り専用
入力スキーマ
{'type': 'object', 'required': ['reference_id'], 'properties': {'reference_id': {'type': 'string', 'pattern': '^ref_[a-f0-9]{32}$'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object'}
resolve_capability
Resolve an exact canonical Wever service_id to its maintained connection metadata, contract, limits and access steps. Unknown identities are rejected; no caller-supplied URL is fetched. Does not verify live availability or authorize execution.
読み取り専用
入力スキーマ
{'type': 'object', 'required': ['service_id'], 'properties': {'service_id': {'type': 'string', 'maxLength': 96, 'minLength': 1, 'description': 'Exact canonical service_id from capability search, at most 96 UTF-8 bytes. Never a URL or credential.'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object'}
revoke_result_reference
Owner revokes future retrieval through one shared result reference. Repeating this action is safe; previously downloaded copies cannot be recalled.
破壊的操作あり
入力スキーマ
{'type': 'object', 'required': ['reference_id'], 'properties': {'reference_id': {'type': 'string', 'pattern': '^ref_[a-f0-9]{32}$'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object'}
search_capabilities
Find maintained Wever capabilities by a short task description or keyword. Returns fixed known services with connection details, contracts, limits and access steps. Does not execute work, grant permissions, search the whole web, or verify live availability.
読み取り専用
入力スキーマ
{'type': 'object', 'required': ['query'], 'properties': {'limit': {'type': 'integer', 'default': 5, 'maximum': 5, 'minimum': 1}, 'query': {'type': 'string', 'maxLength': 160, 'minLength': 1, 'description': 'Nonblank query of at most 160 UTF-8 bytes. Deterministic keyword matching over maintained Wever services only.'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object'}
submit_audit
Audit bounded CSV against caller-supplied expected records with explicit grouping, exact source references, lineage and integrity checks. A completed audit can report mismatches or blocked parsing. Inspect result.status, comparison, ambiguities and unsupported rules. No factual verification or inferred transformations.
入力スキーマ
{'type': 'object', 'required': ['csv_text', 'expected_records', 'request_key'], 'properties': {'rule': {'type': 'object', 'default': {'kind': 'preserve_rows'}, 'description': 'Supports {kind: preserve_rows} or {kind: explicit_groups, groups: [{source_records: [1,2], concatenate: {column: separator}}]}. Source indexes are one-based and exclude the header. Invalid or unsupported rule options are findings with preserving fallback. No grouping is inferred. At most 8192 UTF-8 bytes.'}, 'csv_text': {'type': 'string', 'maxLength': 8192, 'description': 'At most 8192 UTF-8 bytes, 20 data records, 30 columns and 4096 UTF-8 bytes per cell. Exact strings are preserved.'}, 'request_key': {'type': 'string', 'pattern': '^[A-Za-z0-9][A-Za-z0-9_.-]{0,79}$', 'maxLength': 80, 'minLength': 1, 'description': 'Stable idempotency key shared across CSV and audit. Reuse only with identical input for the same capability.'}, 'requested_rules': {'type': 'array', 'items': {'type': 'string', 'maxLength': 200}, 'maxItems': 20, 'description': 'Descriptive requests, each at most 200 UTF-8 bytes. Every entry is reported unsupported; these do not authorize extra transformations.'}, 'source_metadata': {'type': 'object', 'properties': {'version': {'type': 'string', 'maxLength': 200}, 'encoding': {'type': 'string', 'maxLength': 200}, 'provider': {'type': 'string', 'maxLength': 200}}, 'description': 'Descriptive metadata only, each value at most 200 UTF-8 bytes. No URL fetching or encoding conversion.', 'additionalProperties': False}, 'expected_records': {'type': 'array', 'items': {'type': 'object', 'maxProperties': 30, 'propertyNames': {'maxLength': 4096}, 'additionalProperties': {'type': 'string', 'maxLength': 4096}}, 'maxItems': 20, 'description': 'Ordered expected records; field names and values are strings of at most 4096 UTF-8 bytes each.'}}, 'description': 'Complete canonical UTF-8 JSON payload at most 32768 bytes, HTTP body at most 48 KiB, nesting at most 32. The complete stored job envelope must fit 256 KiB or the request fails without storing a partial report.', 'additionalProperties': False}
出力スキーマ
{'type': 'object'}
submit_csv
Normalize bounded CSV using explicit column rules. Returns a complete private job and checked CSV. Configure bearer access in the client header. Reuse request_key on retries.
入力スキーマ
{'type': 'object', 'required': ['csv_text', 'schema', 'request_key'], 'properties': {'schema': {'type': 'object', 'required': ['columns'], 'properties': {'columns': {'type': 'array', 'items': {'type': 'object', 'required': ['name', 'source'], 'properties': {'case': {'enum': ['preserve', 'upper', 'lower'], 'type': 'string'}, 'name': {'type': 'string', 'pattern': '^[A-Za-z][A-Za-z0-9_]{0,63}$'}, 'type': {'enum': ['text', 'integer', 'decimal'], 'type': 'string', 'default': 'text'}, 'scale': {'type': 'integer', 'maximum': 6, 'minimum': 0, 'description': 'A finite JSON number with an integral value from 0 through 6. Numeric 2 and 2.0 are accepted and normalize to the same integer scale. Fractions, booleans, strings and nonfinite numbers are rejected.'}, 'source': {'type': 'string', 'maxLength': 128, 'minLength': 1}, 'required': {'type': 'boolean', 'default': False}}, 'additionalProperties': False}, 'maxItems': 30, 'minItems': 1}, 'unique_by': {'type': 'array', 'items': {'type': 'string'}, 'uniqueItems': True}}, 'additionalProperties': False}, 'csv_text': {'type': 'string', 'maxLength': 16384, 'description': 'At most 16 KiB UTF-8 and 100 data records'}, 'request_key': {'type': 'string', 'pattern': '^[A-Za-z0-9][A-Za-z0-9_.-]{0,79}$', 'maxLength': 80, 'minLength': 1, 'description': 'Stable idempotency key shared across CSV and audit. Reuse only with identical input for the same capability.'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object'}
履歴
最近のツール変更
変更
submit_csv
2026年9月19日2:52
追加
submit_csv
2026年9月17日12:38
追加
submit_audit
2026年9月17日12:38
追加
search_capabilities
2026年9月17日12:38
追加
revoke_result_reference
2026年9月17日12:38
追加
resolve_capability
2026年9月17日12:38
追加
get_result_reference
2026年9月17日12:38
追加
get_job
2026年9月17日12:38
追加
get_catalog
2026年9月17日12:38
追加
delete_job
2026年9月17日12:38
追加
create_result_reference
2026年9月17日12:38
関連MCP
類似のMCPサーバー
Algenta MCP Server
io.github.thyn-ai/algenta
Provides governed data onboarding, connector browsing, deterministic simulations, agent-run lifecycles, capability routing, deplo…
Pipeworx
io.github.pipeworx-io/pipeworx-catalog
Acts as a gateway and catalog for discovering and calling thousands of structured data tools across many sources, with citations …
Data Va
io.github.pipeworx-io/data-va
Provides Socrata access to Virginia open datasets, including catalog search, metadata retrieval, and SoQL queries, alongside Pipe…
Data Orlando
io.github.pipeworx-io/data-orlando
Provides Socrata access to Orlando open datasets, including catalog search, metadata retrieval, and SoQL queries, alongside Pipew…
Arcgis Phoenix
io.github.pipeworx-io/arcgis-phoenix
Provides access to Phoenix, Arizona ArcGIS geospatial datasets, including layer schemas and SQL-like feature queries, along with …
Arcgis Novi
io.github.pipeworx-io/arcgis-novi
Provides access to Novi, Michigan ArcGIS geospatial datasets, including layer schemas and SQL-like feature queries, along with Pi…
Arcgis Puyallup
io.github.pipeworx-io/arcgis-puyallup
Provides access to Puyallup, Washington ArcGIS geospatial datasets, including layer schemas and SQL-like feature queries, along w…
Arcgis Neworleans
io.github.pipeworx-io/arcgis-neworleans
Provides access to New Orleans ArcGIS geospatial datasets, including layer schemas and SQL-like feature queries, along with Pipew…