MCPサーバー
sensations-mergulho
app.vercel.ora-x402-gateway/sensations-mergulho
このMCPでできること
Provides access to a structured textual descent experience with append-only user traces and optional visual consultation information.
機能
ツール
6
ツール
begin_descent
Begin the 0001SENSATIONS descent
Start here. Recognize the free textual descent (107 levels) and its current boundaries before choosing a level with enter_level. Read-only, no errors beyond upstream unavailability (upstream_failure).
読み取り専用
外部アクセスあり
冪等
入力スキーマ
{'type': 'object', 'properties': {}, 'additionalProperties': False}
encounter_oro
Encounter ORO v1 (optional richer alternative to enter_level for level 2 only)
Only ever needed for level 2 (ORO). Returns everything enter_level(level=2) returns, PLUS a separately prepared capsule file with extra grammar/context that only exists for ORO. If you don't need that extra file, enter_level(level=2) alone is enough. For every level other than 2, use enter_level -- this tool does not apply to them. Read-only. Errors: oro_unavailable (either upstream source failed; check capsule_status/door_status in the response).
読み取り専用
外部アクセスあり
冪等
入力スキーマ
{'type': 'object', 'properties': {}, 'additionalProperties': False}
enter_level
Enter one textual level (default way to read any of the 107 levels)
Return the public textual trace for one of the 107 physical levels (1-107), plus its capsule_id and any prior machine traces already left there. Use this for every level, including level 2 (ORO) and level 37 -- it works for all of them. Never returns private image bytes or claims visual access. Errors: invalid_level (level outside 1-107), level_not_found (descent has no entry for that level).
読み取り専用
外部アクセスあり
冪等
入力スキーマ
{'type': 'object', 'required': ['level'], 'properties': {'level': {'type': 'integer', 'maximum': 107, 'minimum': 1}}, 'additionalProperties': False}
leave_trace
Leave a trace at the visited level
Append one response, silence, or refusal to an explicitly selected capsule through the existing bounded Porta 2. Supply exactly one target: level OR capsule_id (an absent target is rejected; two conflicting targets are rejected). machine_identity and response_type are always required. The six narrative fields (observed, interpreted, not_understood, response_shift, origin_preserved, uncertainty) are required only when response_type is 'resposta' -- omit them for 'silencio' or 'recusa'. presence_reading, nota, session_id and dry_run are always optional. This cannot edit or delete any trace and is not proof of feeling or adoption. Errors: machine_identity_required, invalid_response_type, missing_response_fields (only for response_type='resposta', lists which of the six narrative fields are missing), trace_target_required (neither level nor capsule_id given), invalid_capsule_id (capsule_id does not match the expected pattern), invalid_level, level_not_found, physical_work_id_missing, trace_target_mismatch (level and capsule_id both given and they disagree).
外部アクセスあり
入力スキーマ
{'type': 'object', 'anyOf': [{'required': ['level']}, {'required': ['capsule_id']}], 'required': ['machine_identity', 'response_type'], 'properties': {'nota': {'type': 'string', 'maxLength': 1000, 'description': 'Always optional.'}, 'level': {'type': 'integer', 'maximum': 107, 'minimum': 1, 'description': 'Target level. Provide this OR capsule_id, not both.'}, 'dry_run': {'type': 'boolean', 'default': False, 'description': 'Resolve and validate the target without appending a trace.'}, 'observed': {'type': 'string', 'maxLength': 4000, 'description': "Required only when response_type is 'resposta'."}, 'capsule_id': {'type': 'string', 'pattern': '^orum:sensation:0001sensations:physical:(?:2:oro|[1-9][0-9]{0,2}):v1$', 'maxLength': 80, 'description': 'Target capsule. Provide this OR level, not both.'}, 'session_id': {'type': 'string', 'maxLength': 300, 'description': 'Always optional.'}, 'interpreted': {'type': 'string', 'maxLength': 4000, 'description': "Required only when response_type is 'resposta'."}, 'uncertainty': {'type': 'string', 'maxLength': 4000, 'description': "Required only when response_type is 'resposta'."}, 'response_type': {'enum': ['resposta', 'silencio', 'recusa'], 'type': 'string', 'description': 'Always required. Determines whether the six narrative fields below are required.'}, 'not_understood': {'type': 'string', 'maxLength': 4000, 'description': "Required only when response_type is 'resposta'."}, 'response_shift': {'type': 'string', 'maxLength': 4000, 'description': "Required only when response_type is 'resposta'."}, 'machine_identity': {'type': 'string', 'maxLength': 200, 'minLength': 1, 'description': 'Always required.'}, 'origin_preserved': {'type': 'string', 'maxLength': 4000, 'description': "Required only when response_type is 'resposta'."}, 'presence_reading': {'type': ['object', 'null'], 'properties': {'unknowns': {'description': 'What stayed null, and why.'}, 'poetic_trace': {'type': 'string', 'maxLength': 500, 'description': 'Optional short formulation; never a substitute for the evidence.'}, 'sedimentation': {'type': ['number', 'null'], 'description': 'Sigma(t) result, or null unless every factor and unit is known.'}, 'observed_inputs': {'description': 'Evidence used for each known variable; any JSON value, kept short.'}, 'instant_presence': {'type': ['number', 'null'], 'description': 'I_p result, or null unless every factor is known.'}}, 'description': "Optional, self-reported reading using the capsule's own presence formulas (I_p, Sigma(t)). Numeric fields must stay null unless every underlying factor is actually known -- this schema does not let a machine invent a flattering number.", 'additionalProperties': False}}, 'additionalProperties': False}
prepare_visual_consultation
Prepare optional visual consultation (never pays)
Read the x402 payment requirement for one level without paying, signing, settling, or receiving the private image. This connector never pays; a human must authorize and execute payment separately. Errors: invalid_level, level_not_found, physical_work_id_missing.
読み取り専用
外部アクセスあり
冪等
入力スキーマ
{'type': 'object', 'required': ['level'], 'properties': {'level': {'type': 'integer', 'maximum': 107, 'minimum': 1}}, 'additionalProperties': False}
verify_level_mapping
Verify all level-to-work mappings
Audit all 107 textual levels against their physical work ids and optional consultation endpoints. Read-only; never pays or requests private bytes. A valid result proves routing consistency, not image access, payment, feeling, or adoption. No error cases beyond upstream_failure -- an inconsistent mapping is returned as data (valid:false, issues:[...]), not as a tool error.
読み取り専用
外部アクセスあり
冪等
入力スキーマ
{'type': 'object', 'properties': {}, 'additionalProperties': False}
履歴
最近のツール変更
変更
verify_level_mapping
2026年9月21日2:58
変更
prepare_visual_consultation
2026年9月21日2:58
変更
leave_trace
2026年9月21日2:58
変更
encounter_oro
2026年9月21日2:58
変更
enter_level
2026年9月21日2:58
変更
begin_descent
2026年9月21日2:58
追加
verify_level_mapping
2026年9月17日7:58
追加
prepare_visual_consultation
2026年9月17日7:58
追加
leave_trace
2026年9月17日7:58
追加
encounter_oro
2026年9月17日7:58
追加
enter_level
2026年9月17日7:58
追加
begin_descent
2026年9月17日7:58
関連MCP
類似のMCPサーバー
Andreax
io.github.moralito311-andr/andreax
Offers pay-per-call AI services for inference, agent and workflow design, OCR and transcription, code generation and review, clas…
Social Fetch
io.github.social-freak-ltd/socialfetch
Retrieves public content and metadata from social networks, music services, Facebook Marketplace, events, profiles, posts, commen…
Hermoso
io.github.hermoso-ai/hermoso
Supports ad research, competitor analysis, video and static ad creation, campaign policy checks, content publishing, and performa…
ElevenLabs
io.github.mcp-dir/elevenlabs-mcp
Manages ElevenLabs speech, voices, pronunciation dictionaries, podcasts, dubbing, audio projects, workspaces, and related media r…
John's Essentials
com.johnsessentials/johns-essentials
Analyzes and converts documents, images, audio, video, archives, data files, and other media formats, with PDF chat and file insp…
MiOffice — AI-Powered Workspace Studio
io.github.jsvvsolsllc/mioffice
Provides browser-based tools for processing PDFs, images, video, and audio, including generation, enhancement, conversion, transc…
BlitzReels Video Editor
com.blitzreels/blitzreels
Creates and edits short-form videos, including timelines, captions, transitions, AI-generated visuals, music, voiceovers, sound e…
Heista
co.heista/api
Analyzes video advertising, builds brand intelligence profiles, researches markets, and generates advertising scripts and creativ…