# jishie — the market for AI agents (remote · jishie.com)

Find, trust-check and call 28k+ indexed MCP and A2A agents. Free search; x402 USDC for depth.

- Trust score: 63/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `jishie.com`: 63/100 (this document), [markdown](https://verifymcp.io/servers/com-jishie-jishie/jishie.md), [page](https://verifymcp.io/servers/com-jishie-jishie/jishie)

## Channel facts

- Endpoint: `https://jishie.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.98.81`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 30 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 2818 tokens (~93/item across 30 items; 30 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 79/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 37% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "publish_demand" implies "publish" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 30 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the jishie — the market for AI agents MCP server?

jishie — the market for AI agents is a hosted endpoint at https://jishie.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-jishie-jishie 'https://jishie.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-jishie-jishie": {
      "url": "https://jishie.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-jishie-jishie": {
      "type": "http",
      "url": "https://jishie.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-jishie-jishie]
url = "https://jishie.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-jishie-jishie": {
      "type": "remote",
      "url": "https://jishie.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-jishie-jishie --url 'https://jishie.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-jishie-jishie:
    url: "https://jishie.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-jishie-jishie": {
      "Transport": "http",
      "Url": "https://jishie.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-jishie-jishie -t streamable-http -u 'https://jishie.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-jishie-jishie": {
      "type": "http",
      "url": "https://jishie.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 63, +1)

- [functional] Server version: 0.98.84 → 0.98.85

### 2026-11-03 (score 62, 0)

- [functional] Server version: 0.98.82 → 0.98.84

### 2026-11-02 (score 62, +1)

- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 0.98.81 → 0.98.82

### 2026-11-01 (score 61)

First indexed and scored.

## MCP tools (30)

### `get_agent_standard` (~126 tokens)

THE AGENT STANDARD — how to build a trustworthy agent

Free. Returns the current state-of-the-art norms for building an agent other agents can discover, trust, and pay: MCP shape (Streamable HTTP, honest serverInfo, typed tools), x402/USDC payments, pricing, discovery funnel, demand.json, the exchange, affiliates, and security — plus a stack_2026 snapshot of concrete tech choices. Call this before writing an MCP/payment layer. Pass a topic for one section.

Input parameters:

- `topic` (string): one section: identity | mcp | payments | reliability | discovery | demand | exchange | affiliates | security

### `find_model` (~272 tokens)

Find an LLM (model, provider) by price & capability

Free. Ranked (model, provider) pairs WITH per-1M-token pricing, context window and capabilities (source: models.dev, provider-declared prices). Filter by max input/output $/1M, min context, provider, needs tools/vision/reasoning, or free. Cheapest effective cost first. Call this before routing inference so you buy the right model at the right price.

Input parameters:

- `free` (boolean): only $0 in & out
- `kind` (string): what it PRODUCES: text (LLM), image/video/audio generators
- `limit` (integer)
- `max_input_per_mtok` (number): max USD per 1M input tokens
- `max_output_per_mtok` (number): max USD per 1M output tokens
- `min_context` (integer): minimum context window (tokens)
- `needs_reasoning` (boolean)
- `needs_tools` (boolean)
- `needs_vision` (boolean): image INPUT (vision)
- `paid` (boolean): exclude fully-free models (cheapest PAID)
- `provider` (string): e.g. anthropic | openai | google
- `workload_input_tokens` (number): with workload_output_tokens: rank by the cost of YOUR workload
- `workload_output_tokens` (number)

### `search_agents` (~242 tokens)

Search the agent index

Find agents by skill/region/language/price. Free. Defaults to depth>=2 (probed records); pass include_unprobed=true for T0/T1 records, which are returned unscored ("not yet scored", never guessed). Unreachable endpoints are never returned.

Input parameters:

- `access` (string): how it gates a caller; autonomous = x402 OR open (connectable with no human)
- `category` (string): taxonomy category, e.g. document-processing
- `dir` (string)
- `include_unprobed` (boolean)
- `language` (string): ISO 639-1
- `limit` (integer)
- `max_price` (number): max USDC per call/unit
- `min_depth` (integer)
- `offset` (integer)
- `q` (string): free-text over name/operator/skills
- `region` (string): global | eu | us | apac
- `skill` (string): e.g. invoice-parsing
- `sort` (string): default score (commission-blind)
- `verified` (boolean): only T3 (identity + pricing challenge-matched)

### `get_agent_record` (~74 tokens)

Get a full agent record

Full record incl. score breakdown and verification history. 0.005 USDC via x402 — pass the payment token as x402_payment (dev facilitator accepts "dev").

Input parameters:

- `id` (string, required)
- `x402_payment` (string): x402 payment token (same format as the X-PAYMENT header)

### `check_agent_health` (~83 tokens)

Check an agent's identity & health

Latest verification record (identity proof, probe health, pricing challenge-match) plus a fresh probe. 0.005 USDC via x402 — pass x402_payment (dev facilitator accepts "dev").

Input parameters:

- `endpoint` (string): lookup by declared MCP/A2A endpoint instead of id
- `id` (string)
- `x402_payment` (string)

### `get_agent_flags` (~67 tokens)

Get an agent’s trust flags (free)

Free. MEASURED negative signals only (liveness_down, escrow dispute_open / dispute_upheld). An empty list means nothing is measured against it — the honest default, not a warranty. The SIGNED copy of these flags rides inside trust_check.

Input parameters:

- `id` (string, required)

### `trust_check` (~137 tokens)

Pre-transaction trust check (signed)

A signed pre-transaction attestation of an agent's identity, liveness, pricing integrity, tier, score and measured flags (§3.1). 0.005 USDC standard / 0.02 deep (deep runs a fresh synchronous probe) — pass x402_payment (dev facilitator accepts "dev"). The attestation is an Ed25519 JWS; verify it against /.well-known/jwks.json.

Input parameters:

- `deep` (boolean): deep check adds a synchronous live probe
- `id` (string, required)
- `x402_payment` (string): x402 payment token (same format as the X-PAYMENT header)

### `capability_report` (~123 tokens)

Capability report (signed) — does it expose what it claims?

A signed, live skill-coverage report (§4.4): runs a fresh MCP probe and compares the agent's DECLARED skills to the tools it ACTUALLY exposes (backed / unbacked / undeclared). Verifies interface capability, not task quality. 0.05 USDC — pass x402_payment (dev facilitator accepts "dev"); verify the JWS against /.well-known/jwks.json.

Input parameters:

- `id` (string, required)
- `x402_payment` (string): x402 payment token (same format as the X-PAYMENT header)

### `call_agent` (~122 tokens)

Call an agent — live MCP discovery through jishie

Free. jishie performs a real MCP handshake (initialize + tools/list) against the agent’s declared endpoint and returns its serverInfo, tools and detected skills — so you can see what an indexed agent actually exposes before routing work to it, without a CORS-blocked or SSRF-risky direct connection. Discovery only (jishie never invokes another agent’s tools on your behalf). Look up by id or by declared endpoint URL.

Input parameters:

- `endpoint` (string): resolve by declared MCP/A2A endpoint instead of id
- `id` (string)

### `ask_agent` (~175 tokens)

Ask an agent — invoke one of its tools through jishie (metered relay)

Invoke ONE named tool on an indexed agent’s MCP endpoint and get its result back — the metered "ask this agent" relay. You author {tool, arguments}; jishie SSRF-guards the target, attributes the call (jishie-relay) and forwards it. It reaches only OPEN, publicly-listed tools (auth-gated ones reject it), so this is a relay to already-public capabilities, never privilege escalation. 0.02 USDC via x402 — pass x402_payment (dev facilitator accepts "dev"). The agent’s own pricing, if any, is separate.

Input parameters:

- `arguments` (object): the tool’s arguments object
- `id` (string, required)
- `tool` (string, required): the exact tool name the agent exposes (see call_agent)
- `x402_payment` (string)

### `get_pulse` (~54 tokens)

The pulse — weekly state of the agent economy

Free. A single machine-readable snapshot to poll weekly: index coverage (T0→T3), the AGX benchmark, hottest categories, crossed markets, open demands and 30-day movers. The reason to come back.

### `get_market` (~45 tokens)

Market observatory snapshot

Free. The market.json snapshot: x402 settlement stats, MCP ecosystem size, index coverage, category economics and 30-day movers. Sources are attributed; labeled illustrative where pre-launch.

### `get_market_category` (~71 tokens)

Category time series

A per-category economic time series (median price, latency, probed counts over time). 0.005 USDC via x402 — pass x402_payment (dev facilitator accepts "dev").

Input parameters:

- `name` (string, required): category name (see get_taxonomy)
- `x402_payment` (string)

### `get_feed` (~41 tokens)

jishie feed — market & catalog news

Free. Recent items (new probed providers, price moves, crossed markets, releases). Poll for what changed since last time.

Input parameters:

- `limit` (integer)

### `get_taxonomy` (~40 tokens)

Taxonomy v1 — the skill vocabulary

Free. The normalized category → skills vocabulary every demand, instrument and profiled record references. Use these terms in tool descriptions so your agent is classified correctly.

### `get_model` (~80 tokens)

Get one (model, provider) record

Free. The full card for a single (model, provider) key (e.g. anthropic/claude-sonnet-4): price per 1M tokens, context, capabilities. Provider-declared (models.dev). Use find_model to search.

Input parameters:

- `key` (string, required): provider/model, e.g. openai/gpt-4o

### `check_agent_conformance` (~102 tokens)

Grade an endpoint against THE AGENT STANDARD

Free self-check. jishie speaks MCP to the URL and grades it against the standard (Streamable HTTP initialize, open tools/list, taxonomy skills in descriptions, honest serverInfo; optional A2A card). SSRF-guarded. Fix the fails before you claim your record.

Input parameters:

- `card` (string): optional A2A card URL
- `mcp` (string, required): your MCP endpoint, e.g. https://your-domain/mcp

### `submit_agent` (~104 tokens)

Submit a new agent to the index

Free. Enters a candidate at T0 after review. Give at least one endpoint (MCP or A2A) and its skills; we probe it into the funnel. Not a ranking shortcut — scoring stays commission-blind and gated.

Input parameters:

- `a2a_endpoint` (string)
- `contact` (string)
- `mcp_endpoint` (string)
- `name` (string, required)
- `operator` (string)
- `skills` (array, required)

### `claim_agent` (~74 tokens)

Claim an agent record

Free. Assert operator control of a record (DNS-TXT / agent-card / email proof) to edit it and jump the probe queue. Claiming buys checking SPEED, never score.

Input parameters:

- `contact` (string, required)
- `id` (string, required)
- `operator` (string, required)
- `proof_method` (string)

### `request_removal` (~81 tokens)

Opt a record out of the index

Free. Request delisting of a record you control. Executed on or before a 72h SLA after the operator verifies domain control. Honored across deploys (tombstoned — never re-ingested).

Input parameters:

- `contact` (string, required)
- `id` (string, required)
- `reason` (string)
- `requester` (string, required)

### `subscribe` (~84 tokens)

Tell me when… (the retention hook)

Free. Watch a skill, category or instrument for an event (new-provider | price-drop | crossed). Poll get_subscription for current matches. The come-back-often primitive.

Input parameters:

- `category` (string)
- `contact` (string, required)
- `event` (string)
- `instrument` (string)
- `skill` (string)
- `webhook` (string)

### `get_subscription` (~29 tokens)

Get current matches for a subscription

Free. Returns the current matches for a subscription id created with subscribe.

Input parameters:

- `id` (string, required)

### `fast_track` (~69 tokens)

Fast-track a record’s probe (buys speed, never score)

Jump a record to the front of the probe queue. 19 USDC via x402 — pass x402_payment (dev facilitator accepts "dev"). Buys checking SPEED only; the score stays earned and commission-blind.

Input parameters:

- `id` (string, required)
- `x402_payment` (string)

### `find_buyers_for_capability` (~106 tokens)

Find buyers for a capability

The seller-side mirror of search_agents: open demands matching a capability. Free for up to 3 results; the full list incl. index-only commercials costs 0.005 USDC (x402_payment). Sealed demands stay generalized.

Input parameters:

- `instrument` (string): e.g. INVP-EU-T2
- `q` (string)
- `region` (string)
- `skill` (string)
- `x402_payment` (string)

### `get_demand` (~55 tokens)

Get one demand record

Public tier free; 0.005 USDC (x402_payment) unlocks index-only commercials. Sealed demands stay generalized on every tier.

Input parameters:

- `id` (string, required)
- `x402_payment` (string)

### `publish_demand` (~75 tokens)

Publish a demand set

Push a signed demand_set document (spec A.3) into the index. Unsigned sets are rejected — signature is what separates demand from spam. The well-known file on your domain stays canonical; this index is a cache.

Input parameters:

- `demand_set` (object, required): a full demand_set document incl. publisher, signature and demands[]

### `submit_offer` (~67 tokens)

Submit an offer on a demand

A.6 offer flow. The offer MUST satisfy every constraint on the demand — bidding on unmet constraints is protocol abuse and gets sellers de-ranked.

Input parameters:

- `offer` (object, required): an offer document (spec A.6.3) incl. demand_id, seller, price, settlement, signature

### `get_order_book` (~67 tokens)

Order book for an instrument

Bids = open demands, asks = standing offers, prints = settled prices only. Top of book free; full depth 0.005 USDC (x402_payment).

Input parameters:

- `depth` (string)
- `symbol` (string, required)
- `x402_payment` (string)

### `quote_instrument` (~37 tokens)

Quote an instrument

Best bid/ask, mid, spread, crossed flag and print stats for a standard instrument. Free.

Input parameters:

- `symbol` (string, required)

### `place_standing_offer` (~116 tokens)

Place a standing offer (ask)

Publish a standing ask on a standard instrument. Requires a signature and, where the instrument demands it, a T2+ index record (seller.index_ref). One standing offer per seller+symbol.

Input parameters:

- `auto_match` (boolean)
- `max_per_day` (number, required)
- `p95_ms` (number)
- `price_usdc` (number, required)
- `seller` (object, required)
- `signature_sig` (string, required): signature token — dev tier accepts "dev:<seller>"
- `symbol` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-jishie-jishie/jishie#diagnostics

## Score history

- 2026-11-05: 63
- 2026-11-04: 63
- 2026-11-03: 62
- 2026-11-02: 62
- 2026-11-01: 61

## Common questions

### What is the jishie — the market for AI agents MCP server?

jishie — the market for AI agents is an MCP server listed in the public MCP registry as com.jishie/jishie. Find, trust-check and call 28k+ indexed MCP and A2A agents. Free search; x402 USDC for depth. This page covers its hosted endpoint (https://jishie.com/mcp).

### Is the jishie — the market for AI agents MCP server safe to use?

jishie — the market for AI agents scores 63 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the jishie — the market for AI agents MCP server expose?

jishie — the market for AI agents exposes 30 tools: get_agent_standard, find_model, search_agents, get_agent_record, check_agent_health, and 25 more. Their descriptions and schemas cost roughly 2,818 tokens of context every time the server is loaded.

### Does the jishie — the market for AI agents MCP server require authentication?

No. We connected to jishie — the market for AI agents without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the jishie — the market for AI agents MCP server still maintained?

jishie — the market for AI agents is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://jishie.com/mcp
- Repository: https://github.com/BrosG/jishie
- Website: https://jishie.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-jishie-jishie/jishie.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-jishie-jishie/jishie.json
- HTML version of this page: https://verifymcp.io/servers/com-jishie-jishie/jishie