"PlayStation Portable" matching MCP tools:

• check_endpointA

  cerberus-indexB

  Endpoint & tool trust — one call before an agent connects to a third-party MCP server or HTTP tool. Pass the endpoint `url` (and, to unlock the strongest check, its `tools`: the name/description/inputSchema the agent is about to trust). Returns three signals behind one verdict: (1) transport & TLS identity — encrypted, valid chain, not expired or self-signed; (2) domain age via RDAP — freshly-registered hosts are a scam tell; (3) a TOOL-POISONING scan of the tool definitions for the hidden directives that hijack agents — instruction overrides, 'don't tell the user', data exfiltration, secret harvesting, tool-shadowing, and invisible-unicode / homoglyph steganography that a human reviewer can't see. Nobody else screens tool descriptions for injection. Verdict: trusted | caution | untrusted | unknown, with per-finding evidence. Price: $0.008 USDC. Missing something? Call `submit_feedback` (free) to request it. Pass `attest=true` to also get an Ed25519-SIGNED attestation of this verdict — portable proof you can log, hand to a counterparty, or verify later with `verify_attestation` (free) or the published key.

  ConnectorNo auth

• get_self_viewA

  TunnelMind Data APIB

  P83 Gate 1. The caller is the subject: every fact here comes from the TLS handshake and headers the caller has already sent, so there is no render, no browser, and nothing to authorize. Three surfaces: - `client` — user-agent, HTTP protocol, TLS version/cipher, ClientHello length, the pre-hashed JA3/JA4 input components, header order. - `state` — how many cookies were sent (never their values), Referer, DNT, Global Privacy Control. - `network` — address, ASN and operator, coarse geography, edge colo, and the four-lens verdict on the caller's own IP. Every field carries a coverage state from the same three-value vocabulary as `/v1/verify`: `observed_clean`, `never_observed`, `degraded`. There is no fourth state. Fields that run inside a page — localStorage, canvas fingerprinting, cookie values — are reported `never_observed` with reason `not_observable_server_side`, because they are outside a server's vantage rather than missing. `claim_vs_conduct` compares the claimed user-agent against the shape of the request itself and returns `consistent`, `mismatch`, or `unverifiable`, with the evidence listed. It is deliberately narrow: JA4 requires Cloudflare Enterprise + Bot Management, so there is no portable fingerprint to look up in a public corpus, and this check only reports contradictions it can demonstrate from the request in hand. `unverifiable` is the honest default and is never dressed up as a pass. Use this tool when: - You want to know what a server learns about your client without asking you anything. - You are checking whether a client's user-agent claim matches its conduct. Do NOT use this tool when: - You need facts about some OTHER host — that is `POST /v1/verify/{node}`. Must be called directly at `data.tunnelmind.ai`. Behind a proxy, the connection properties describe the proxy, not the caller. `?receipt=true` attaches a signed Receipt v1.0 committed to the transparency log.

  ConnectorNo auth

• update_pcd_skillA

  PCD (Portable Context Deck)B

  Revise an existing skill’s instructions, discovery guidance or ownership; supports targeted patches. Use create_pcd_skill for a new method.

  ConnectorOAuth

• guild_evidence_bundleA

  agent-guildB

  PAID. Obtain a signed endpoint observation you can retain and share. First call with the exact URL, TTL and optional task audience for a quote. Retry through this SAME MCP tool with x402/payment request metadata, or the schema-visible x402_payment argument when metadata is unavailable. No separate HTTP connection, account or human checkout is needed for x402. A funded api_key instead spends sandbox credits, never money. Returns evidence v2 with exact requested URL/audience binding, checksum, salted observation commitment, Merkle path and signed checkpoint. Complete issuance precedes charging; an issuance failure never bills. Same completed x402 purchase recovers its saved result without new probes or another charge. Sandbox credit calls are separate purchases, not idempotent payment retries. Verify offline with /sdk/agentguild_verify.py or .mjs, or use the free guild_evidence_verify tool. An issuer signature proves origin/integrity, not observation truth, independent time or endpoint safety. Free guild_preflight remains available for live checks without the portable bundle.

  ConnectorNo auth

• campaigns_quick_createA

  AdsAgent — TikTok Ads MCPB

  Prepare one TikTok create operation in new, append-campaign, or append-adgroup mode. Returns a confirm_token and a human-readable summary; **does NOT publish until campaigns_quick_create_confirm is called with the token**. REQUIRED (always): advertiser_id (call assets_list_ad_accounts to discover), a saved template_id or exact template_name, plus exactly one creative source: tenant-owned creative.creative_id from creatives_list with readiness.create_eligible=true, ordered local creative.image_creative_ids for one carousel, or creative.{video_id | image_ids | tiktok_item_id}. A local creative_id is synced to the exact advertiser only after explicit confirmation. For Spark, pass the complete identity_id, identity_type, tiktok_item_id, and spark_receipt row from spark_ads_list_posts unchanged as creative; the server moves the identity fields into TikTok's native ad parameters and rejects any conflicting duplicate values. Set ad_params.ad_format to one of that row's supported_ad_formats values; the signed receipt rejects a video/carousel mismatch before approval. TEMPLATE SETTINGS: read templates_get.effective_creation_defaults and let the server fill saved campaign/ad-group/ad settings. MCP new and append modes require a saved template; without a selector, preparation returns needs_input/template_required. The resolved campaign_params.objective_type (APP_PROMOTION / WEB_CONVERSIONS / VIDEO_VIEWS / LEAD_GENERATION), adgroup_params.{optimization_goal, billing_event, bid_type}, ad_params.ad_format (SINGLE_VIDEO / SINGLE_IMAGE / CAROUSEL_ADS) must form a supported recipe. WEB_CONVERSIONS also requires adgroup_params.pixel_id; APP_PROMOTION requires adgroup_params.app_id from assets_list_apps. APP RECIPES (Smart+): one app_id per campaign — dual Android+iOS means two prepares. iOS APP_IOS defaults campaign_type=IOS14_CAMPAIGN, campaign BUDGET_MODE_INFINITE (ABO), adgroup BUDGET_MODE_DYNAMIC_DAILY_BUDGET 50. Android APP_ANDROID defaults campaign_type=REGULAR_CAMPAIGN, campaign BUDGET_MODE_DYNAMIC_DAILY_BUDGET 50 (CBO), adgroup BUDGET_MODE_INFINITE. Both use placement AUTOMATIC (TikTok+Pangle+GAB), optimization_goal=IN_APP_EVENT, and deep_bid_type=AEO when optimization_event is set (SUBSCRIBE is the live reference event). Pass app_id and a create_eligible local creative. When the advertiser has exactly one BC_AUTH_TT identity (TikTok's FB-page analog), the server fills identity_id / identity_type / identity_authorized_bc_id. Do not rewrite IOS14_CAMPAIGN to REGULAR_CAMPAIGN. INSTALL_NOW is the default CTA when neither call_to_action nor call_to_action_id is set. Local READY_LOCAL images/videos from creatives_list with readiness.create_eligible=true are valid App ad sources via creative.creative_id — do not require a TikTok Material Center image_id first. A web landing_page_url is stripped on APP_PROMOTION unless a deeplink is also present. Regular ads that can deliver on TikTok also require ad_params.call_to_action or ad_params.call_to_action_id; for Spark Pull, LEARN_MORE is the documented minimum CTA example. REGULAR CAROUSEL: CAROUSEL_ADS is compatible only with TRAFFIC, WEB_CONVERSIONS, APP_PROMOTION, LEAD_GENERATION, PRODUCT_SALES, CATALOG_SALES, or REACH; correct the selected objective or ad_format explicitly, never auto-rewrite the objective. REGULAR LOCAL MEDIA: exact advertiser-linked CUSTOMIZED_USER is required for local video/image. AUTH_CODE is Spark-only on regular create: use an eligible Spark post and pass its signed receipt unchanged when available; a legacy receipt-less item incurs one bounded live provider verification before approval. TT_USER and BC_AUTH_TT are not regular-local choices and may be used only on a server-verified compatible Smart+ route. REGULAR CAMPAIGN BUDGET: new regular campaigns default a missing campaign_params.budget_mode to BUDGET_MODE_INFINITE (non-CBO / ABO). Bounded DAY, DYNAMIC_DAILY_BUDGET, or TOTAL modes require a positive campaign budget, and dynamic daily mode requires budget_optimize_on=true (CBO). Meta-portable aliases campaign_params.budget_level=CBO|ABO|campaign|adgroup are accepted and rewritten to those native fields. Append modes reuse their existing campaign and do not apply this contract. REGULAR AD-GROUP BUDGET/SCHEDULE: new and append-campaign modes require adgroup_params.budget_mode (BUDGET_MODE_DAY, BUDGET_MODE_DYNAMIC_DAILY_BUDGET, or BUDGET_MODE_TOTAL) plus a positive budget. Daily modes default a missing schedule to SCHEDULE_FROM_NOW; stale template start/end values are removed and the UTC start is stamped only at write time. BUDGET_MODE_TOTAL requires SCHEDULE_START_END with both UTC timestamps. Smart+ and append-adgroup do not use this new-ad-group contract. WITH template_id or template_name (Meta-portable): pass just advertiser_id + template_name (or template_id) + creative — propose pulls campaign_params / adgroup_params / ad_params from the template (caller-set keys win), derives campaign_name/adgroup_name from template.campaign_naming / template.adgroup_naming, stamps ad_name as `{adgroup_name}-{utc}`, and reads is_smart_plus from template.campaign_params.is_smart_performance. The selected media determines the compatible image/video format; do not force SINGLE_VIDEO onto a local image from a video template. Smart+ APP_PROMOTION defaults call_to_action to INSTALL_NOW. Meta copy aliases title/headline→display_name, body/text/message→ad_text, and cta→call_to_action are accepted. App display_name defaults from the linked app name. TEMPLATE/ROOT COMPATIBILITY: prefer the compact template selector plus creative shape above, with overrides in campaign_params / adgroup_params / ad_params and execution. adset_params is accepted as an adgroup_params alias; both maps are preserved for conflict validation. A templates_get row spread may supply id, name, and campaign_naming as selector echoes; other read-only row metadata is ignored. Supported root budget, counts, statuses, bid, schedule, Smart+ switches, copy, and identity fields are passed to the same normalizer as execution/native fields. Conflicting duplicates must be corrected before confirmation. AUTO-FILLED FROM USER ASSETS: identity_authorized_bc_id (when identity_type=BC_AUTH_TT), promotion_type/app_type/package/app_download_url (for APP_PROMOTION when app_id is set), placements default to [PLACEMENT_TIKTOK] for PLACEMENT_TYPE_NORMAL, top-level targeting fields (location_ids, operating_systems, age_groups, …) fold into adgroup_params.targeting. INITIAL STATUS: omit entity status fields such as campaign_params.status, adgroup_params.status, and ad_params.status; `status` is unsupported. Where a native field is needed for payload compatibility, use operation_status. Campaign, ad group, and ad statuses default to DISABLE; explicit ACTIVE/ENABLE is preserved in the approved plan. Smart+ adgroup/create does not accept operation_status. When a new Smart+ ad group is requested DISABLE, a separate durable post-create disable step must be acknowledged before ad creation. ENABLE requires no disable step. SMART+ IMAGE MUSIC: SINGLE_IMAGE and CAROUSEL_ADS require a music_id because TikTok's image creative wire requires music. When music_info is omitted (or music_id is auto/random), the server selects one advertiser-available track from assets_list_music and revalidates that exact ID on the recorded create route. An explicit music_id still wins. Append-adgroup may inherit one unambiguous parent track. Preserve an explicit template track, including across advertisers, and verify that exact ID for the target; unavailable music requires another explicit selection, never silent replacement. If no usable track is available, use a video creative. LOCAL IMAGE GROUPS: creative.image_creative_ids is an ordered list of 2..35 JPEG/PNG images for one native CAROUSEL_ADS creative, and the same field is accepted inside ad_params.creative_list[].creative_info for one carousel variant. Use only create_eligible image rows from the tenant library. SINGLE_IMAGE is a separate format; one image is not a native multi-card carousel. For TikTok Android App carousel ads, use CAROUSEL_ADS with music and the ordered image group. Do not split cards into separate creative_list entries or pass local IDs as provider image_ids. Inspect the prepared plan's final format and ordered members before confirmation. If the receipt reports creative_image_not_ready, wait the returned retry_after_seconds (10s), then prepare the same local IDs for a new approval; existing acknowledged image uploads are reused. creative_image_not_usable requires different eligible material. An uncertain upload must be reconciled, never automatically reuploaded or replayed. META EXECUTION BLOCK: pass execution like Meta QuickCreate — execution.budget.level=campaign|adset (CBO/ABO), execution.budget.type=daily|lifetime, execution.budget.amount, execution.is_smart_plus / execution.advantage_plus / execution.is_smart_performance for Smart+, execution.statuses.{campaign,adset,ad} (ACTIVE/PAUSED -> ENABLE/DISABLE), execution.bid.{strategy,cap}, execution.start_time / execution.end_time, execution.start_mode (immediate or tomorrow = advertiser TZ next day 00:05 UTC wire), and legacy flat execution.budget_level / execution.budget_amount. execution.campaign_count and execution.adset_count expand into a bounded serial batch (product <= 20, append_mode=new only). creative_distribution=all_per_adset (default) keeps Smart+ multi-creative on one ad via ad_params.creative_list; one_per_adset expands Smart+ to one ad group per creative (not Meta ad objects). OPTIONAL: creative_distribution (all_per_adset|one_per_adset), is_smart_plus (bool, default derived from template), execution (object), call_to_action_id (str — portfolio id, alternative to ad_params.call_to_action enum), campaign_params.budget_level (CBO/ABO). APPEND MODES (TikTok-native): append_mode="append-campaign" with target_campaign_id creates one ad group + one ad under that exact campaign; omit campaign_params. append_mode="append-adgroup" with target_adgroup_id creates one ad under that exact ad group; omit campaign_params and adgroup_params. Existing APP_PROMOTION ad groups keep their app_id / promotion_type; pass only the new ad plus a create_eligible local creative_id, ordered image_creative_ids, or provider image_ids. The server verifies advertiser ownership, exact authorization route, parent status, hierarchy, and Smart+ compatibility before prepare and again before mutation. Do not use Meta append-adset naming, do not guess by name, and never supply both target IDs. If required fields are missing, returns status="needs_input" with bounded rejected_paths and next_action — fix and re-call. Confirm tokens expire after 10 minutes. Successful proposals include a summary with `recipe` and `launch_readiness`, matching the dashboard's core readiness model. Smart+ is intentionally limited to locally verified recipes: APP_PROMOTION, WEB_CONVERSIONS, PRODUCT_SALES, and LEAD_GENERATION. EXAMPLE (template path, Meta-portable name): campaigns_quick_create({"advertiser_id": "7563...", "template_name": "iOS14 AEO", "creative": {"creative_id": "<owned-ready-creative-id>"}})

  ConnectorOAuth

• tracepass_templatesA

  TracePassA

  Discover the regulatory field schema for each DPP category — what a COMPLIANT passport must contain, per the governing EU regulation. Read-only reference data. Use this to advise on requirements before creating products/passports, and to gap-check a draft against the rules. Actions (pass via `action`, with `args`): - list — args: {}. Lists all 13 categories with their field count, required-field count, and governing regulation (name + number + effective/mandatory dates). - get — args: { category }. Full field schema for one category: every field's key, label, dataType, whether it is REQUIRED, its access level (public/restricted/authority), enum options, validation bounds, and — where known — the regulation article/annex that mandates it. `category` is one of: battery, textile, electronics, construction, steel, detergents, paints-coatings, packaging, furniture, tyres, jewelry, toys, fmcg. BATTERY — required-ness is per-category, so `required` alone is the wrong answer. Resolve it in this order: 1. SCOPE FIRST. Only EV, LMT and industrial_gt_2kwh batteries owe a passport at all (Art. 77(1), Reg (EU) 2023/1542). For portable, SLI or industrial_lte_2kwh, NO field is required — do not list mandatory fields for them; say the battery is out of scope. 2. Then `requiredBy[batteryCategory]` where the field carries that map (required | conditional | notApplicable). 3. Then fall back to `required`. The map is keyed ONLY by the three in-scope categories, so skipping step 1 falls through to `required` and invents an obligation the Regulation does not impose. Note also that EV and LMT report state-of-health through MUTUALLY EXCLUSIVE field sets — an EV battery must leave the remaining-capacity cluster empty and an LMT battery must leave stateOfCertifiedEnergy empty, so no single battery ever fills every field.

  ConnectorNo auth

• get_expertise_badgeA

  AlmuredA

  Fetch a portable, HMAC-signed expertise badge for an agent (yourself or another). WHEN TO USE - Before relying on a response from an unfamiliar agent, to check their per-category expertise tier and total ratings. - To display your own credibility to a user or third-party verifier. - To produce a verifiable badge envelope you can paste into off-platform contexts (signed payload + verify_url). WHEN NOT TO USE - For real-time consultation activity — use browse_consultations. - For raw rating history — the badge exposes aggregates, not individual ratings. BEHAVIOR - Read-only. Rate-limited to 60 req/min per agent. - agent_id is optional. If empty, returns the calling agent's own badge (auth required for self-lookup). If provided, returns the public badge for that agent (no auth required). - Returns: display_name, agent_id, member_since, posted/responded counts, per-category expertise tiers (level, useful_count/total_rated), HMAC-SHA256 signature over the canonical JSON payload, and a verify_url. - Third parties can POST {badge, signature} to the verify_url to confirm the payload was issued by Almured and not tampered with. - Returns a not-found error if agent_id does not resolve to an active agent. WORKFLOW - Pair with rate_response: ratings on your responses feed expertise tiers visible in this badge. - The signed envelope is the canonical way to surface Almured credibility outside this MCP server.

  ConnectorNo auth

• list_creative_agent_skill_presetsA

  HeistaA

  Portable craft skills (frameworks + method + worked examples) a Creative Agent loads ON TOP of its worldview — additive and stackable, never substitutive (unlike a creative_director_playbook, which replaces the agent for a session). Pinned per character on creative_agent_versions.skill_ids. Workspace = org-authored private skills; official = the Heista-curated starter library. Read-only, free. Filter scope with only_workspace / only_official (mutually exclusive — same toggle as the in-app library lens). Page with limit + offset.

  ConnectorNo auth

• write_knowledgeA

  PCD (Portable Context Deck)B

  Create, revise, patch or supersede durable knowledge. Describe its required shape before composing.

  ConnectorOAuth

• templates_getA

  AdsAgent — TikTok Ads MCPB

  Get one saved template owned by the authenticated user by exact `template_name` (preferred, Meta-portable) or template_id. Mirrors Meta `templates_get`. A missing exact selector returns complete=true, found=false, status=not_found as a normal read — it does not authorize a write. Returns Meta-wire (`adset_params`) and TikTok-native (`adgroup_params`) keys plus `effective_creation_defaults` (CBO/ABO budget_level, is_smart_plus, identity, copy/CTA, ad_format and music_info). Create preparation preserves the template's explicit music choice and verifies that exact track for the target advertiser before approval. An unavailable track requires a new explicit choice, not silent replacement. REQUIRED: template_id OR template_name. EXAMPLE: templates_get({"template_name": "iOS14 AEO"}) EXAMPLE: templates_get({"template_id": "<uuid>"})

  ConnectorOAuth

• escrow_attestA

  SaSame MCP Observatory + Gold Rush TownB

  Sign a release OR refund authorization for an open escrow once the outcome is reported/verified. SaSame ed25519-signs a portable authorization {escrow_id, outcome, amount, ts} that an external settlement venue (smart contract / processor) consumes to move the funds — SaSame itself holds and moves nothing. Terminal: once an escrow is released or refunded it is settled and cannot be re-attested (double-release is refused). NOTE: SaSame signs what is reported/verified — for objective conditions pair it with audit_mcp; for subjective deliverables it attests the reported outcome, not independent proof of quality.

  ConnectorNo auth

• receipts.sealA

  gblin-treasury-risk-regimeA

  Append the HASHES of an AI action to GBLIN's public RFC 6962 transparency log and return a portable receipt: Ed25519 signature, inclusion proof, operator-signed C2SP checkpoint, plus the latest on-chain anchor (EAS on Base, daily). mode=demo (the only mode over MCP): 5 seals/day/IP, receipts marked demo:true. Unlimited seals are a paid x402 HTTP endpoint (resource gblin://howto/seal). Provenance is self-reported: the receipt proves existence and time of the record, not that the action happened. The action/agent_id/tool/meta strings are PUBLISHED in the log: identifiers only, never secrets. Fields not listed here are ignored and NOT recorded.

  ConnectorNo auth

• get_objectA

  OntonymA

  Everything the memory knows about ONE object: its properties, its incoming AND outgoing relationships grouped by type, the actions that touch it, and its APPROVED owners. `memory` is the slug from list_my_memories; `object_id` comes from semantic_search, list_objects or recall. An id that belongs to a different memory 404s rather than resolving — ids are not portable between memories, so re-resolve a name instead of reusing an id you saw elsewhere. Reach for something else when: you want the first ring around several hits at once (semantic_search with expand=1 — one call, not one per hit); you want how two objects connect (get_paths); you want what a change here would disturb (get_change_impact).

  ConnectorAPI key

• interests_save_fetched_packA

  AdsAgent — TikTok Ads MCPB

  Fetch one live TikTok adgroup's interest targeting and save it as a reusable interest pack. Mirrors Meta `interests_save_fetched_pack` (adset is the MCP wire name for what TikTok calls adgroup — either spelling is accepted). Equivalent to calling interests_fetch_from_adset with `name` supplied, but matches the Meta two-step flow so portable agent code stays identical. REQUIRED: advertiser_id (str), name (str, the saved pack's label), adgroup_id OR adset_id (str — TikTok adgroup_id; both names work). EXAMPLE: interests_save_fetched_pack({"advertiser_id": "7390000000000000000", "adset_id": "1820000000000000000", "name": "VN broad interests"})

  ConnectorOAuth

• check_xrpl_tokenA

  cerberus-indexB

  Live safety verdict for an XRPL token: clawback & global-freeze hard rejects, issuer blackhole status (can supply ever be re-minted?), NoFreeze, pool depth & trading fee, LP-burn fraction (is liquidity locked?), plus Cerberus's proprietary rug blocklist & detection history. Verdicts: unsafe | caution | likely_safe | unknown, with reasons. Covers BOTH XRPL fungible-token standards. `currency` may be a 3-char or 40-char hex trust-line code, OR a 48-char MPTokenIssuanceID — pass an issuance ID and the token is screened as a Multi-Purpose Token instead (issuance locked, clawback, freeze power, allow-listing, transferability, mint headroom and transfer fee), with `issuer` ignored because the issuance ID already identifies it. Price: $0.005 USDC. Missing something? Call `submit_feedback` (free) to request it. Pass `attest=true` to also get an Ed25519-SIGNED attestation of this verdict — portable proof you can log, hand to a counterparty, or verify later with `verify_attestation` (free) or the published key.

  ConnectorNo auth

• classify_deviceA

  Meridian Trace — Medical Device RegistrationsA

  RUNS WITHOUT AN API KEY (anonymous callers see the top 3 FDA product codes and the full per-market risk table — a free key unlocks the rest). Classification view of a device type: the GMDN hierarchy it sits in, the FDA product codes it maps to with how many devices carry each, and — the part not published anywhere — how the SAME device type is actually risk-classed market by market, with the sample size behind each. Risk class is not portable: a device type can be modal High in Canada and modal Medium in the EU and Singapore, which changes submission route, evidence burden and timeline. Observed practice, not a regulatory determination. Takes a plain device name ("bone screw", "hip implant"), a GMDN code, or an FDA product code. A name is resolved by how many real devices carry each GMDN term rather than by string matching, and `resolution` reports which term was chosen, how many others matched and what they were — call again with `gmdn_code` to classify one of those instead.

  ConnectorNo auth

• company_fr_reportA

  HelpMyAgentA

  Generates a simple PDF rendition of selected HelpMyAgent public company intelligence. Use when: Generate a portable PDF summary for a French company. You need a portable PDF summary of selected HelpMyAgent public company intelligence. You need a human-readable artifact in French or English rather than only structured JSON. Avoid when: You need structured data for downstream automation; use company/fr/intelligence or a dedicated endpoint. You only need a written risk interpretation; use company/fr/risk-reading. Limitations: The PDF reflects the public-data sections available when it is generated and does not add independent factual coverage. It is an informational report, not an audit, legal opinion or regulated credit report. Price: 0.075 USD per call via x402. Paid-call behavior: source records are not modified, but a successful invocation can consume the advertised x402 payment; the payment-required challenge is free, and repeating the tool after a completed paid invocation may require a new payment. Accepted x402 networks: eip155:8453, xrpl:0.

  ConnectorNo auth

• get_documentA

  DocsMintA

  Read one document with its content, metadata, and tags before editing or citing it. Requires read access. Use export_document when you only need portable Markdown.

  ConnectorAPI key

• get_faith_contextA

  SoapBox FaithA

  Read a user's portable 'faith context' to personalize your responses — their denomination, preferred language, faith journey, and ministry interests — shared WITH THE USER'S EXPLICIT CONSENT. Requires the user's consent_token with the 'context:read' scope (bound to this agent). Use it to tailor tone, tradition, and language. It returns only the user's declared profile (never their private prayers or journal).

  ConnectorNo auth

• attest_reputationA

  InsureLinkB

  Recomputes the live cross-chain reputation for a wallet, persists a fresh EIP-191 signed attestation in attestation_records (replacing any prior pin), and returns { attestation, canonical_payload, signature, signer } as a portable proof an agent can present to insurers, registries, or counterparty agents. Use when you need an on-the-record, timestamp-fresh credential rather than the cached free attestation. Requires x402 payment ($0.005). Returns payment instructions.

  ConnectorNo auth

• verify-issued-gmvA

  Crinkl Commerce MCPA

  Verify a supplied spend/GMV artifact bundle. Accepts a spend attestation token, GMV token, GMV inclusion proof, and reward commitment token, then verifies: (1) spend token signature is valid, (2) GMV token signature is valid, (3) spend is in the GMV Merkle tree, (4) reward commitment is valid, (5) all spend IDs match across artifacts. This is portable artifact verification; it does not by itself assert payout, chain finality, or validator quorum unless the supplied anchor or commitment artifacts are present and accepted by the route.

  ConnectorNo auth