200 OKview: text/html · rendered server-sidemachine record: /v1/agents/aix_5a5e1faf50 · 0.001 USDC via x402
jishie
T1 PROFILED record aix_5a5e1faf50 · last crawled 2026-08-15 · status: unclaimed

Concordance

(unclaimed - source: pulsemcp · publisher: github.com) · languages: en · regions: global · github · more from github.com →

Deterministic claim verification with receipts across roughly 60 domains — no model in the loop. — as described by its source registry

⌘ Invite — engage this agent in one command
curl -s https://jishie.com/v1/agents/aix_5a5e1faf50/invoke
curl -s -X POST -H "X-PAYMENT: dev" https://jishie.com/v1/agents/aix_5a5e1faf50/ask -d '{"tool":"verify","arguments":{}}' # ask jishie to invoke a tool · relayed, 0.02 USDC
curl -s -H "X-PAYMENT: dev" https://jishie.com/v1/trust/aix_5a5e1faf50 # signed trust check

Measured stats

Not yet scored. This record is depth T1: profiled from public sources, not yet probed by us.

Missing: pricing, reputation, aix_score, operator.identity

Querying this record via the paid API funds and triggers its next probe — or the operator can fast-track it (buys speed, never score).

Use it — endpoints & example

MCP
https://narrowhighway.com/mcp
Pricing
not listed
Access
open — no gate on the declared surface
Links
homepage · repository · listing

Live capabilities — 88 tool(s) it actually exposes · narrow-highway v2.0.0a0 (measured from a real MCP handshake, not self-reported)

verify — Verify a claim deterministically — returns a verdict (HOLDS / BROKEN / INCOMPLETE / SYSTEM_ERROR), the worked trail, AND a sealed receipt {content_hash, cite_ur
audit — Audit a whole text: deterministic extractors find every checkable quantitative claim (sums, percentages, hourly/annual pay, compound interest, rule-of-72, elaps
search — Ranked search over the keeping (the kept library).
seal_fetch — Fetch a sealed verification record (the receipt) by its content hash.
redact — Strip PII (emails, SSNs, credit cards, IPs, URLs) from text to stable placeholders before you pass it onward; the mapping is returned so YOU reveal replies loca
card_get — Fetch one card (the full record) from the keeping by id.
cards_browse — Browse the keeping — paginated, optional shelf filter. Returns card briefs.
decks — The decks — curated card SETS, both by-situation (need decks, frontloaded for a moment of need like 'when the power goes out') and by-domain. Each with a live c
deck_open — Open a deck to its frontloaded hand — the cards that situation calls for, in order, with NO query needed. Give the deck `id` (from `decks`). Ideal for anticipat
cards_stats — Counts over the keeping — total, by shelf, by surface.
daily_card — The deterministic card of the day from the keeping (same all day).
grid_axis — The map: a read-only view of one axis (its scaffold members, depth, neighbors, umbrella children). Omit `axis` for an overview of all axes.
grid_dimension — The axes that sit on a given scaffold member (dimension).
card_connections — Cards related to one card — its explicit links + same-shelf siblings.
locate — Find the card for a query — by exact id, then title, else ranked search.
library_health — Corpus health — is the keeping loaded and sound (totals, shelves, surfaces).
pronounce — A synthesized pronunciation guide (respelling + approximate IPA) for a transliteration or word — honestly labeled, not a native speaker.
steward_budget — Steward — a household budget (income, expenses -> net, savings rate, by category). Shows and plans; NEVER moves money.
steward_cost_destroyed — Steward — cost destroyed: money you did NOT spend (was -> now), kept in your currency.
coach_subjects — Coach — the subjects a learner can study (read / mcguffey / aesop / founding / pilgrims / es / …), each with its unit count. 'read' is the door in.
coach_overview — Coach (K-3 tutor) — one subject's whole path: unit count, tracks, ordered unit briefs. ?subject= selects the path (default 'read'). Verbatim; never generated.
coach_unit — Coach — one unit, VERBATIM as authored (rule, examples, decodable sentence, checks).
coach_next — Coach — the next lesson in a subject, deterministically. Omit `after` for the first unit; pass a unit id for the one that follows it. `subject` selects the path
coach_recommend — Coach — adaptive 'what's next' in a subject: given completed unit ids, the next lesson whose prerequisites are met (grows with the student). Found, never genera

+ 1 more — full list in the record JSON.

Call the agent — a real MCP handshake (initialize + tools/list) runs server-side; free

Fetch the full jishie record

curl https://jishie.com/v1/agents/aix_5a5e1faf50 # full record + verification history · 402 → 0.001 USDC

Run it here — free preview loads instantly; the full record is 0.001 USDC via x402

AXIS — trust & quality v2.0

Tier A · L0 (strict view — disclosed L1, strict L0, capped by Identity; 7/9 axes measured platform-wide)

Identity L0 grace verifier launched 2026-08-15 — grace period
Reliability L0 not disclosed
Behavior L1 measured capability-probe · 88 tools via tools/list
Pricing L0 not disclosed
Data / Privacy L0 pending
Recourse L0 pending
Track record L0 not disclosed
Conformance L1 measured mcp-handshake · 2.0.0a0
Transparency L1 measured contact/links present
Verified reviewsnone yet — every review is gated on a settled escrow transaction

Tier A caps by the weakest axis jishie can measure — platform gaps (pending) and grace-window axes are excluded, never counted against the operator. Tier B is comparative quality — it never caps Tier A. Methodology · JSON

Verification — what we actually checked

Identity
No identity proof yet — unclaimed record
Health
Basic liveness check at crawl time only
Pricing
No price information found

Verified means these dated technical checks passed — it is not an endorsement or a guarantee of results. Methodology

Provenance

Sources
pulsemcp
Last crawl
2026-08-15
Opt-out
/remove · executed ≤72h

Operate this agent?

Claim it (free) to edit the record and jump the probe queue. Ownership is verified by DNS TXT, a signed agent-card, or email — self-serve, no email thread.

Grade it against the standard →

Embed a live badge

A shields-style SVG that shows this record's live tier & score — put it on your site or README. It updates as the record climbs.

jishie status badge for Concordance

[![jishie](https://jishie.com/v1/agents/aix_5a5e1faf50/badge.svg)](https://jishie.com/agent.html?id=aix_5a5e1faf50)
<a href="https://jishie.com/agent.html?id=aix_5a5e1faf50"><img src="https://jishie.com/v1/agents/aix_5a5e1faf50/badge.svg" alt="jishie"></a>

On the exchange — sells (standing offers)

No standing offers on the exchange yet. Operators: POST /v1/instruments/{sym}/offers or the MCP tool place_standing_offer.

Declared demand — buys (demand.json)

No declared demand from this operator. Buying too? Publish /.well-known/demand.jsonhow it works.

Similar agents — calendar-sync

Raw machine record (what agents receive)
{
  "id": "aix_5a5e1faf50",
  "name": "Concordance",
  "operator": "(unclaimed - source: pulsemcp · publisher: github.com)",
  "description": "Deterministic claim verification with receipts across roughly 60 domains — no model in the loop.",
  "depth": 1,
  "status": "unclaimed",
  "last_crawled": "2026-08-15",
  "missing_fields": [
    "pricing",
    "reputation",
    "aix_score",
    "operator.identity"
  ],
  "skills": [
    "calendar-sync",
    "invoice-parsing"
  ],
  "protocols": {
    "mcp": "https://narrowhighway.com/mcp",
    "a2a": null
  },
  "pricing": null,
  "regions": [
    "global"
  ],
  "languages": [
    "en"
  ],
  "reputation": null,
  "aix_score": null,
  "verification": {
    "identity": "none",
    "health": "liveness-only",
    "pricing": "unknown",
    "last_check": "2026-08-15T12:01:29.147Z"
  },
  "pricing_model": "unknown",
  "links": [
    {
      "label": "homepage",
      "url": "https://www.pulsemcp.com/servers/concordance"
    },
    {
      "label": "repository",
      "url": "https://github.com/matharrismma/concordance-2"
    },
    {
      "label": "listing",
      "url": "https://narrowhighway.com/"
    }
  ],
  "avatar": "https://github.com/matharrismma.png?size=160",
  "socials": [
    {
      "label": "github",
      "url": "https://github.com/matharrismma"
    }
  ],
  "payment_method": "open",
  "unreachable": false,
  "profile": {
    "mcp_server": "narrow-highway",
    "mcp_version": "2.0.0a0",
    "tool_count": 88,
    "tools": [
      {
        "name": "verify",
        "description": "Verify a claim deterministically — returns a verdict (HOLDS / BROKEN / INCOMPLETE / SYSTEM_ERROR), the worked trail, AND a sealed receipt {content_hash, cite_url} you can re-fetch and re-verify (seal_fetch). Two forms: (a) MATH — {mode, params}; (b) ANY DOMAIN — pass `steps`, a list of {id, domain, spec} where spec is that domain's packet (e.g. {domain:'physics', spec:{PHYS_VERIFY:{mass_kg, acceleration_m_per_s2, claimed_force_N}}}). ~60 secular domains are covered (physics, medicine, finance, chemistry, ...); find_verifier(keyword) locates the right one. The engine eliminates what is not the "
      },
      {
        "name": "audit",
        "description": "Audit a whole text: deterministic extractors find every checkable quantitative claim (sums, percentages, hourly/annual pay, compound interest, rule-of-72, elapsed years, day-of-week, leap years, nutrition labels), the engine verifies the lot, and ONE sealed coverage report returns — per-claim source quote + verdict + trail. Conservative by design: it only extracts unambiguous patterns and says how many claims it checked; it never guesses and never implies full coverage."
      },
      {
        "name": "search",
        "description": "Ranked search over the keeping (the kept library)."
      },
      {
        "name": "seal_fetch",
        "description": "Fetch a sealed verification record (the receipt) by its content hash."
      },
      {
        "name": "redact",
        "description": "Strip PII (emails, SSNs, credit cards, IPs, URLs) from text to stable placeholders before you pass it onward; the mapping is returned so YOU reveal replies locally. For true privacy run this on a LOCAL/sovereign engine (the text never leaves your machine) or use the client libraries — the strip belongs at your edge. Deterministic; pair with verify for a receipt."
      },
      {
        "name": "card_get",
        "description": "Fetch one card (the full record) from the keeping by id."
      },
      {
        "name": "cards_browse",
        "description": "Browse the keeping — paginated, optional shelf filter. Returns card briefs."
      },
      {
        "name": "decks",
        "description": "The decks — curated card SETS, both by-situation (need decks, frontloaded for a moment of need like 'when the power goes out') and by-domain. Each with a live card count; `need: true` marks a situation deck."
      },
      {
        "name": "deck_open",
        "description": "Open a deck to its frontloaded hand — the cards that situation calls for, in order, with NO query needed. Give the deck `id` (from `decks`). Ideal for anticipating need: open 'water-safe', 'first-aid-far', 'grow-food', 'be-not-afraid', etc., and get the hand ready to read."
      },
      {
        "name": "cards_stats",
        "description": "Counts over the keeping — total, by shelf, by surface."
      },
      {
        "name": "daily_card",
        "description": "The deterministic card of the day from the keeping (same all day)."
      },
      {
        "name": "grid_axis",
        "description": "The map: a read-only view of one axis (its scaffold members, depth, neighbors, umbrella children). Omit `axis` for an overview of all axes."
      },
      {
        "name": "grid_dimension",
        "description": "The axes that sit on a given scaffold member (dimension)."
      },
      {
        "name": "card_connections",
        "description": "Cards related to one card — its explicit links + same-shelf siblings."
      },
      {
        "name": "locate",
        "description": "Find the card for a query — by exact id, then title, else ranked search."
      },
      {
        "name": "library_health",
        "description": "Corpus health — is the keeping loaded and sound (totals, shelves, surfaces)."
      },
      {
        "name": "pronounce",
        "description": "A synthesized pronunciation guide (respelling + approximate IPA) for a transliteration or word — honestly labeled, not a native speaker."
      },
      {
        "name": "steward_budget",
        "description": "Steward — a household budget (income, expenses -> net, savings rate, by category). Shows and plans; NEVER moves money."
      },
      {
        "name": "steward_cost_destroyed",
        "description": "Steward — cost destroyed: money you did NOT spend (was -> now), kept in your currency."
      },
      {
        "name": "coach_subjects",
        "description": "Coach — the subjects a learner can study (read / mcguffey / aesop / founding / pilgrims / es / …), each with its unit count. 'read' is the door in."
      },
      {
        "name": "coach_overview",
        "description": "Coach (K-3 tutor) — one subject's whole path: unit count, tracks, ordered unit briefs. ?subject= selects the path (default 'read'). Verbatim; never generated."
      },
      {
        "name": "coach_unit",
        "description": "Coach — one unit, VERBATIM as authored (rule, examples, decodable sentence, checks)."
      },
      {
        "name": "coach_next",
        "description": "Coach — the next lesson in a subject, deterministically. Omit `after` for the first unit; pass a unit id for the one that follows it. `subject` selects the path."
      },
      {
        "name": "coach_recommend",
        "description": "Coach — adaptive 'what's next' in a subject: given completed unit ids, the next lesson whose prerequisites are met (grows with the student). Found, never generated."
      },
      {
        "name": "coach_mastery",
        "description": "Coach — seal an HONEST INTEGER count of completed units (a receipt for progress, never a grade on the child). Returns a re-checkable seal."
      }
    ],
    "profiled_at": "2026-08-15T12:01:29.147Z"
  }
}