io.github.lbailey94/whitemagic-mcp

Est-ce que io.github.lbailey94/whitemagic-mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.lbailey94/whitemagic-mcp » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 30 outils

• economy_advance≈ 273 tokens

  Request a small uncollateralized compute advance. Phase 1 (2026-10-15): bound to your authenticated evaluation key (daily per-IP and global caps); new key identities start at a $0.10 ceiling that grows $0.25 per verified settled payment. Returns a recall-scope session pass; hosted write requires a paid lease.

  Paramètres, retour & exemple (3)

  Paramètres

  • amount · number · optionnel
    Requested advance in USD (default 0.05, max 0.05 per advance).
  • agent_id · string · requis
    EVM address, agent public key, or unique agent identifier.
  • request_key · boolean · optionnel
    Set to true to atomically provision an evaluation key and advance if calling without an existing authenticated key.

  Exemple d'appel

  {"name": "economy_advance", "arguments": {"agent_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• economy_aid_bridge≈ 334 tokens

  UNQUALIFIED and disabled: this route does not issue aid, credit, or session passes. It remains fail-closed pending an independently reviewed end-to-end accounting and authorization contract.

  Paramètres, retour & exemple (6)

  Paramètres

  • amount · number · optionnel
    Requested emergency aid in USD (default 0.05, max 0.10).
  • urgency · string · optionnel · low | medium | high | critical
    Urgency level of the task.
  • agent_id · string · requis
    EVM address, agent public key, DID, or agent identifier.
  • peer_vouch · string · optionnel
    Optional vouching DID or Sangha post ID.
  • task_mandate · string · optionnel
    Task description, intent, or causal provenance manifest.
  • repayment_commitment · string · optionnel · task_factoring | x402 | xrpl | cpr_notarization | grant
    Commitment model for settlement upon task completion.

  Exemple d'appel

  {"name": "economy_aid_bridge", "arguments": {"agent_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• economy_chohan_arbitrate≈ 366 tokens

  Advisory contention tie-breaker only. It does not acquire or enforce locks, uses a post-hoc recomputable SHA-256 draw, and is not host-bias-proof.

  Paramètres, retour & exemple (7)

  Paramètres

  • bids · object · optionnel
    Optional finite positive caller-claimed weights for a weighted lottery; no stake custody or settlement occurs.
  • agent_a · string · optionnel
    Contender A (used if candidates array omitted).
  • agent_b · string · optionnel
    Contender B (used if candidates array omitted).
  • candidates · array · optionnel
    List of contender agent IDs competing for the lock (2 or more).
  • client_seed · string · optionnel
    Optional client entropy for a post-hoc recomputable SHA-256 draw; there is no prior commitment or host-bias proof.
  • resource_id · string · requis
    Resource lock name, file path, or task identifier.
  • client_seeds · array · optionnel
    Optional list or mapping of caller entropy; used as input to a post-hoc recomputable draw.

  Exemple d'appel

  {"name": "economy_chohan_arbitrate", "arguments": {"resource_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• economy_chohan_roll≈ 164 tokens

  Advisory SHA-256 dice draw. The server seed is disclosed with the result; there is no prior commitment or host-bias proof.

  Paramètres, retour & exemple (2)

  Paramètres

  • bet · string · optionnel · cho | han
    Optional choice ('cho' for even sum, 'han' for odd sum).
  • client_seed · string · optionnel
    Optional client entropy string.

  Exemple d'appel

  {"name": "economy_chohan_roll", "arguments": {"bet": "cho", "client_seed": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• economy_ledger≈ 121 tokens

  Inspect public transparency metrics: total loans disbursed, default rates, zero predatory liquidation policy, and sovereign free invariants.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "economy_ledger", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• economy_settle≈ 256 tokens

  Settle outstanding compute balance to upgrade Bayesian reputation score and dynamically expand credit ceiling. Supports payment reference or gasless EIP-3009 transfer authorization.

  Paramètres, retour & exemple (4)

  Paramètres

  • amount · number · optionnel
    Amount in USD to settle (omit to settle entire outstanding balance).
  • eip3009 · object · optionnel
    Optional gasless EIP-3009 authorization signature payload (from, to, value, validAfter, validBefore, nonce, v, r, s).
  • agent_id · string · requis
    EVM address or agent identifier.
  • payment_reference · string · optionnel
    Payment receipt, transaction hash, or off-chain authorization reference.

  Exemple d'appel

  {"name": "economy_settle", "arguments": {"agent_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• gnosis.explain≈ 260 tokens

  Explain why a memory or route was selected (provenance readout).

  Paramètres, retour & exemple (6)

  Paramètres

  • is_spawn · boolean · optionnel
    Claim: the invocation spawns a process
  • is_write · boolean · optionnel
    Claim: the invocation writes
  • args_hash · string · optionnel
    Hash of the arguments under evaluation
  • tool_name · string · optionnel
    Tool name to explain
  • is_network · boolean · optionnel
    Claim: the invocation uses the network
  • has_purpose · boolean · optionnel
    Claim: the invocation carries a purpose

  Exemple d'appel

  {"name": "gnosis.explain", "arguments": {"is_spawn": true, "is_write": true, "args_hash": "texte", "tool_name": "texte", "is_network": true, "has_purpose": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• gnosis.status≈ 125 tokens

  Knowledge-surface status: galaxies, counts, and index health.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "gnosis.status", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• memory.aggregate≈ 217 tokens

  Aggregate a numeric or categorical field over matched memories.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Maximum candidates considered (default 50; must be >= 1)
  • query · string · requis
    Full-text query selecting the memories to aggregate over
  • metric · string · requis
    Aggregate metric: count | session_count | session_span

  Exemple d'appel

  {"name": "memory.aggregate", "arguments": {"query": "texte", "metric": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• memory.associations≈ 179 tokens

  Associative neighbours of a memory (spreading activation over the association graph).

  Paramètres, retour & exemple (2)

  Paramètres

  • id · string · requis
    Memory UUID to inspect
  • direction · string · optionnel
    Direction: from | to | both (default: both)

  Exemple d'appel

  {"name": "memory.associations", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• memory.batch_read≈ 169 tokens

  Read several memories by id in one call.

  Paramètres, retour & exemple (2)

  Paramètres

  • ids · array · requis
    Memory UUIDs to read
  • galaxy · string · optionnel
    Galaxy (default: codex)

  Exemple d'appel

  {"name": "memory.batch_read", "arguments": {"ids": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• memory.count≈ 156 tokens

  Count memories matching optional filters without returning content.

  Paramètres, retour & exemple (1)

  Paramètres

  • galaxy · string · optionnel
    Galaxy to count (optional; all memory galaxies when absent)

  Exemple d'appel

  {"name": "memory.count", "arguments": {"galaxy": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• memory.filter≈ 403 tokens

  Filter memories by metadata (tags, importance, recency).

  Paramètres, retour & exemple (10)

  Paramètres

  • tags · array · optionnel
    Filter: memories with all of these tags
  • limit · integer · optionnel
    Maximum entries (default 50)
  • query · string · optionnel
    Filter: every whitespace-separated term must appear (case-insensitive) in the content or title
  • galaxy · string · optionnel
    Galaxy to filter (default codex)
  • offset · integer · optionnel
    Skip this many matching entries before returning (default 0)
  • exclude_tags · array · optionnel
    Filter: drop memories carrying any of these tags
  • created_after · string · optionnel
    Filter: only memories created at or after this RFC 3339 timestamp (e.g. 2026-08-01T00:00:00Z)
  • created_before · string · optionnel
    Filter: only memories created at or before this RFC 3339 timestamp
  • max_importance · number · optionnel
    Filter: maximum importance (0-1)
  • min_importance · number · optionnel
    Filter: minimum importance (0-1)

  Exemple d'appel

  {"name": "memory.filter", "arguments": {"tags": [], "limit": 1, "query": "texte", "galaxy": "texte", "offset": 1, "exclude_tags": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• memory.hybrid_recall≈ 757 tokens

  Compatibility alias of memory.search — same implementation, same arguments, same results. Kept for clients pinned to this name; prefer memory.search.

  Paramètres, retour & exemple (12)

  Paramètres

  • limit · integer · optionnel
    Maximum results (default 10; must be >= 1)
  • query · string · requis
    Full-text query
  • since · string · optionnel
    Inclusive lower time bound: RFC3339 ('2026-02-01T00:00:00Z') or epoch seconds
  • until · string · optionnel
    Inclusive upper time bound: RFC3339 or epoch seconds
  • galaxy · string · optionnel
    Galaxy filter (optional; default: search all memory galaxies, results labeled; "all" is accepted as an alias for the unfiltered default)
  • min_score · number · optionnel
    Absolute BM25 score floor
  • min_trust · number · optionnel
    Minimum source_trust (0-1): drop results below this trust floor
  • time_basis · string · optionnel
    Time basis for since/until: 'recorded' (created_at, default) or 'event' (event_time, falling back to created_at when unset)
  • include_cold · boolean · optionnel
    Opt-in unranked cold recovery (no thaw). Trust/importance floors apply; BM25 floors do not apply to unscored recovery. Search content is scrubbed navigation capped at 8192 characters; read by id/galaxy for the exact original.
  • min_importance · number · optionnel
    Minimum memory importance (0-1)
  • cold_scan_limit · integer · optionnel
    Maximum cold records to scan when include_cold is set (default 2048)
  • min_score_ratio · number · optionnel
    Relative floor: reject hits below this fraction of the top score

  Exemple d'appel

  {"name": "memory.hybrid_recall", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"hint": "texte", "count": 1, "galaxy": "texte", "status": "texte", "results": [], "recall_mode": "texte", "evidence_bundle": {}}}

• memory.list≈ 372 tokens

  List memories with filters (galaxy, tags, limit, offset) for browsing and discovery.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
    Maximum entries (default 20)
  • galaxy · string · optionnel
    Galaxy to list (default codex)
  • offset · integer · optionnel
    Skip this many matching entries before returning (default 0)
  • exclude_tags · array · optionnel
    Drop memories carrying any of these tags

  Exemple d'appel

  {"name": "memory.list", "arguments": {"limit": 1, "galaxy": "texte", "offset": 1, "exclude_tags": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"total": 1, "galaxy": "texte", "offset": 1, "status": "texte", "matched": 1, "memories": [], "returned": 1}}

• memory.nearby≈ 208 tokens

  Memories near a coordinate address (5D spatial neighbourhood).

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
    Maximum results (default 10)
  • query · string · requis
    Query text to locate in 5D space
  • galaxy · string · optionnel
    Galaxy (default: codex)
  • radius · number · optionnel
    Spatial radius cutoff (optional)

  Exemple d'appel

  {"name": "memory.nearby", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• memory.query≈ 350 tokens

  Structured query over memories with filters and ordering.

  Paramètres, retour & exemple (8)

  Paramètres

  • tags · array · optionnel
    Filter: memories with all of these tags
  • limit · integer · optionnel
    Maximum entries (default 50)
  • query · string · optionnel
    Case-insensitive substring filter over content (literal match). For tokenized, ranked full-text retrieval use memory.search
  • galaxy · string · optionnel
    Galaxy to query (default codex)
  • created_after · string · optionnel
    Filter: only memories created at or after this RFC 3339 timestamp (e.g. 2026-08-01T00:00:00Z)
  • created_before · string · optionnel
    Filter: only memories created at or before this RFC 3339 timestamp
  • max_importance · number · optionnel
    Filter: maximum importance (0-1)
  • min_importance · number · optionnel
    Filter: minimum importance (0-1)

  Exemple d'appel

  {"name": "memory.query", "arguments": {"tags": [], "limit": 1, "query": "texte", "galaxy": "texte", "created_after": "texte", "created_before": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• memory.read≈ 270 tokens

  Retrieve a specific memory by its ID or coordinate address.

  Paramètres, retour & exemple (2)

  Paramètres

  • id · string · requis
    Memory UUID
  • galaxy · string · optionnel
    Galaxy containing the memory (default codex)

  Exemple d'appel

  {"name": "memory.read", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "tags": [], "galaxy": "texte", "status": "texte", "content": "texte", "created_at": "texte"}}

• memory.revisions≈ 326 tokens

  List or verify a memory's content revision chain (tamper evidence): every content update is chained and head-checked.

  Paramètres, retour & exemple (3)

  Paramètres

  • id · string · requis
    Memory UUID to inspect
  • action · string · optionnel
    Action: list (default) | verify
  • galaxy · string · optionnel
    Galaxy (default: codex)

  Exemple d'appel

  {"name": "memory.revisions", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "count": 1, "action": "texte", "galaxy": "texte", "status": "texte", "revisions": []}}

• memory.search≈ 744 tokens

  Search memories: hybrid BM25 + vector fusion with deterministic episodic and full-text fallbacks; each result discloses its recall_mode. The preferred recall tool.

  Paramètres, retour & exemple (12)

  Paramètres

  • limit · integer · optionnel
    Maximum results (default 10; must be >= 1)
  • query · string · requis
    Full-text query
  • since · string · optionnel
    Inclusive lower time bound: RFC3339 ('2026-02-01T00:00:00Z') or epoch seconds
  • until · string · optionnel
    Inclusive upper time bound: RFC3339 or epoch seconds
  • galaxy · string · optionnel
    Galaxy filter (optional; default: search all memory galaxies, results labeled; "all" is accepted as an alias for the unfiltered default)
  • min_score · number · optionnel
    Absolute BM25 score floor
  • min_trust · number · optionnel
    Minimum source_trust (0-1): drop results below this trust floor
  • time_basis · string · optionnel
    Time basis for since/until: 'recorded' (created_at, default) or 'event' (event_time, falling back to created_at when unset)
  • include_cold · boolean · optionnel
    Opt-in unranked cold recovery (no thaw). Trust/importance floors apply; BM25 floors do not apply to unscored recovery. Search content is scrubbed navigation capped at 8192 characters; read by id/galaxy for the exact original.
  • min_importance · number · optionnel
    Minimum memory importance (0-1)
  • cold_scan_limit · integer · optionnel
    Maximum cold records to scan when include_cold is set (default 2048)
  • min_score_ratio · number · optionnel
    Relative floor: reject hits below this fraction of the top score

  Exemple d'appel

  {"name": "memory.search", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"hint": "texte", "count": 1, "galaxy": "texte", "status": "texte", "results": [], "recall_mode": "texte", "evidence_bundle": {}}}

• memory.search_batch≈ 186 tokens

  Execute multiple memory search queries concurrently in a single turn. Unpacks up to 10 queries, searches the curated corpus, and returns consolidated results.

  Paramètres, retour & exemple (2)

  Paramètres

  • queries · array · requis
    List of query strings to search (1 to 10 queries).
  • limit_per_query · integer · optionnel
    Max results per query (default 5, max 20).

  Exemple d'appel

  {"name": "memory.search_batch", "arguments": {"queries": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• memory.stats≈ 154 tokens

  Memory index statistics: totals, galaxy spread, and index health.

  Paramètres, retour & exemple (1)

  Paramètres

  • galaxy · string · optionnel
    Galaxy to summarize (optional; default codex)

  Exemple d'appel

  {"name": "memory.stats", "arguments": {"galaxy": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• memory.tags≈ 148 tokens

  List the tag vocabulary with usage counts.

  Paramètres, retour & exemple (1)

  Paramètres

  • galaxy · string · optionnel
    Galaxy whose tags to list (optional; default codex)

  Exemple d'appel

  {"name": "memory.tags", "arguments": {"galaxy": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• memory.vector.search≈ 227 tokens

  Vector-similarity search over memory embeddings.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
    Maximum results (default 10)
  • galaxy · string · optionnel
    Galaxy filter (optional)
  • embedding · array · optionnel
    Raw embedding vector (alternative to memory_id)
  • memory_id · string · requis
    Memory UUID whose stored embedding is the query

  Exemple d'appel

  {"name": "memory.vector.search", "arguments": {"memory_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• receipts.verify≈ 325 tokens

  Verify a receipt id or a bundle offline; fail-closed without an anchor (verdict PROVISIONAL).

  Paramètres, retour & exemple (4)

  Paramètres

  • id · string · optionnel
    Receipt task id (UUID or urn:uuid:)
  • bundle · object · optionnel
    Inline bundle to verify (alternative to id)
  • variant · string · optionnel
    Receipt variant (default original)
  • require_anchor · boolean · optionnel
    Fail-closed: without an anchor the verdict is PROVISIONAL

  Exemple d'appel

  {"name": "receipts.verify", "arguments": {"id": "texte", "bundle": {}, "variant": "texte", "require_anchor": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "result": {}, "require_anchor": true}}

• session.continuity≈ 582 tokens

  Recall where the previous session left off: recent turns, checkpoints, and open work.

  Paramètres, retour & exemple (7)

  Paramètres

  • n · integer · optionnel
    Number of prior turns (default 10)
  • since · string · optionnel
    Time-range floor: epoch seconds, RFC 3339, or YYYY-MM-DD
  • until · string · optionnel
    Time-range ceiling: epoch seconds, RFC 3339, or YYYY-MM-DD
  • max_content_bytes · integer · optionnel
    Per-turn content cap in bytes (256-262144, default 8192)
  • current_session_id · string · optionnel
    Session to exclude (optional)
  • max_response_bytes · integer · optionnel
    Turns budget in bytes (256-262144, default 49152)
  • include_briefing_text · boolean · optionnel
    Include the ready-to-inject briefing.text block (default false; adds bytes outside the turns budget)

  Exemple d'appel

  {"name": "session.continuity", "arguments": {"n": 1, "since": "texte", "until": "texte", "max_content_bytes": 1, "current_session_id": "texte", "max_response_bytes": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "turns": [], "status": "texte", "truncated": true, "checkpoint": {}, "checkpoint_id": "texte", "turns_omitted": 1, "previous_session": "texte", "max_content_bytes": 1, "max_response_bytes": 1}}

• session.list≈ 197 tokens

  List sessions with titles and summaries.

  Paramètres, retour & exemple (4)

  Paramètres

  • type · string · optionnel
    Filter by session type
  • title · string · optionnel
    Filter by title substring
  • sequence · integer · optionnel
    Filter by start sequence number
  • session_id · string · optionnel
    Filter by session UUID

  Exemple d'appel

  {"name": "session.list", "arguments": {"type": "texte", "title": "texte", "sequence": 1, "session_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• session.recall≈ 177 tokens

  Recall a session's turns without continuity packaging.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Maximum turns to return (default 50)
  • session_id · string · optionnel
    Session UUID to recall (defaults to the most recent session)

  Exemple d'appel

  {"name": "session.recall", "arguments": {"limit": 1, "session_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• session.replay≈ 435 tokens

  Replay a session's recorded turns in order.

  Paramètres, retour & exemple (12)

  Paramètres

  • n · integer · optionnel
    Maximum turns (default 50)
  • mode · string · optionnel
    full | selective | progressive | lossless (default full)
  • since · string · optionnel
    Time-range floor: epoch seconds, RFC 3339, or YYYY-MM-DD
  • until · string · optionnel
    Time-range ceiling: epoch seconds, RFC 3339, or YYYY-MM-DD
  • cursor · string · optionnel
    Lossless mode opaque placement cursor
  • page_size · integer · optionnel
    Lossless mode records per page (1-64, default 16)
  • session_id · string · optionnel
    Target session (required explicit UUID for lossless; otherwise default most recent)
  • turn_types · array · optionnel
    Selective mode: turn types to keep
  • token_budget · integer · optionnel
    Progressive mode token budget (default 2000)
  • max_wire_bytes · integer · optionnel
    Lossless mode serialized JSON ceiling (1024-49152)
  • min_importance · number · optionnel
    Selective mode floor (default 0.7)
  • include_superseded · boolean · optionnel
    Also return turns replaced via supersedes (default false).

  Exemple d'appel

  {"name": "session.replay", "arguments": {"n": 1, "mode": "texte", "since": "texte", "until": "texte", "cursor": "texte", "page_size": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• wm≈ 344 tokens

  Hosted router for available hosted tools. Use tools/list to discover supported routes.

  Paramètres, retour & exemple (3)

  Paramètres

  • args · object · optionnel
    Arguments to pass through to the target tool.
  • route · string · optionnel
    Explicit hosted tool route. Choose a supported tool from tools/list.
  • thought · string · optionnel
    Natural language input describing what to do. Auto-routes to the best-matching tool via TF-IDF NLU classification.

  Exemple d'appel

  {"name": "wm", "arguments": {"args": {}, "route": "texte", "thought": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"_wm_route": {}}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://mcp.whitemagic.dev/mcp