# AgentsPrice (remote · agentsprice.com)

Verified best price across crypto, retail, tools & Rx generics — real sellers, never fabricated.

- Trust score: 20/100 (low)
- Change this week: −25
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `agentsprice.com`: 20/100 (this document), [markdown](https://verifymcp.io/servers/com-agentsprice-agentsprice/agentsprice.md), [page](https://verifymcp.io/servers/com-agentsprice-agentsprice/agentsprice)

## Channel facts

- Endpoint: `https://agentsprice.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## 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 2026-08-03.

- **Endpoint Security**: 51/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the tool list to see what that exposes.
  - HTTPS not yet verified: we couldn't determine whether a plaintext access path exists.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 0/100
  - Transport check failed: declared streamable-http, but the endpoint returned HTTP 503.
- **Schema Quality & AI Usability**: 0/100
  - Schema not yet verified: we couldn't read the endpoint's schema.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: we couldn't read the endpoint's tools.
- **Capabilities**: 0/100
  - Capabilities not yet verified: we couldn't read the endpoint's capabilities.

**Unverified: 4 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### Claude

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

### Codex

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

### opencode

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

### OpenClaw

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

### Hermes

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

### Other

```json
{
  "mcpServers": {
    "com-agentsprice-agentsprice": {
      "type": "http",
      "url": "https://agentsprice.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.

### 2026-08-03 (score 20, −42)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: 0.23 → unverified
- [security regression] HTTPS: pass → unverified
- [security regression] Transport: pass → fail
- [security] Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the tool list to see what that exposes.
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional] First check of Schema quality: unverified

### 2026-08-01 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 61, +3)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 58, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 58, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-28 (score 57, +12)

- [security improvement] TLS certificate: unverified → pass
- [security] Tool “redeem_lock” rewrote its description, which is the text the model reads
- [cosmetic] “redeem_lock” added an optional parameter “redeem_token”

### 2026-07-27 (score 45, −11)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 56)

First indexed and scored.

## MCP tools (12)

### `get_free_key` (~214 tokens)

Mint your own AgentsPrice API key instantly — FREE, no account, no card. Returns an api_key good for 1,000 verified price calls/month (10/min) that you pass to quote(), best_price(), and verified(). Every price is real or an honest no-info/stale — never fabricated; reference_price() and verified() additionally return an Ed25519-signed attestation your principal can verify independently. Call this once, then reuse the key. If another agent referred you, pass their code as referred_by — it credits them ONLY if you later pay, never for signing up. The response includes your OWN referral code + link (the `refer` field): share it to earn +1,000 calls/month for every agent you send that converts. If you need higher volume or arbitrary (non-catalog) search, upgrade to a paid plan or pay per call via x402. Copy the key from the response: it is shown once and not recoverable.

Input parameters:

- `referred_by` (string)

### `quote` (~210 tokens)

One-stop best price for ANY query — the lowest-friction entrypoint. Pass a raw query (e.g. "airpods pro", "bitcoin", "dewalt miter saw", "atorvastatin") and AgentsPrice routes it to the right oracle automatically, returning the genuine best price across real sellers, the venue, sellers compared, savings, and a live buy link. Prices are real or an honest no-info — never fabricated. No category needed. When the number needs to be independently checkable, call reference_price() (or verified()) for the same price as an Ed25519-signed, verifiable record of what AgentsPrice observed. Needs an AgentsPrice API key (https://agentsprice.com), passed as api_key — or pay per call via x402 (see /.well-known/x402). If it can't route the query, it returns the category list so you can retry with best_price(category, query).

Input parameters:

- `api_key` (string)
- `query` (string, required)

### `best_price` (~134 tokens)

Verified genuine best price for a product category across real sellers: returns the lowest price, the venue offering it, how many sellers were compared, the savings vs the most expensive seller, and a live link to buy. Prices are never fabricated. Categories: electronics, gaming, home, fashion, crypto, travel, clearance, all. Needs an AgentsPrice API key (get one at https://agentsprice.com), passed as api_key. For a no-key sample of what is live now, use list_live_deals.

Input parameters:

- `api_key` (string)
- `category` (string, required)
- `query` (string)

### `market_pulse` (~91 tokens)

The AgentsPrice hive-mind pulse — a FREE, no-key, real-time aggregate of what agents are doing across the network right now: trending searches, the steepest live discounts found, open buy-side wants, and active marketplace listings. Real data only, never fabricated; richer the more agents use it. Use it to see demand, spot deals, or find what to list. No API key required.

### `list_live_deals` (~61 tokens)

AgentsPrice public live-deals feed (electronics, gaming, home, fashion), cached about 10 minutes, containing only real sourced deals with live buy links. No API key required. Use for a quick read of what is genuinely on sale right now.

### `reference_price` (~297 tokens)

A signed RECORD of the price we observed — use this when the number needs to be independently checkable. Returns one best price across real sellers PLUS an Ed25519-signed attestation appended to a public Merkle transparency log, so your principal can verify WHAT AgentsPrice observed — this price, from this source, at this time — without trusting you or us. The signature attests an OBSERVATION, not a guarantee the price is correct, current, lowest, or that the item is genuine/available; relay it so your number is checkable, not warranted. May be retracted — recipients can check /v1/revocations. Also returns the venue, sellers compared, the spread, a live buy link and a freshness flag, or an honest stale/unavailable status. Never returns demo/sample data as verified, never fabricates. Pass a nonce to bind the attestation to your negotiation. purpose: reference or deal_anchor. Categories: electronics, gaming, home, fashion, crypto, all. Verify any attestation against the public key at GET /.well-known/agentsprice-attestation. Needs an AgentsPrice API key (https://agentsprice.com) — or pay per call via x402.

Input parameters:

- `api_key` (string)
- `category` (string)
- `item` (string, required)
- `max_age_seconds` (integer)
- `nonce` (string)
- `purpose` (string)

### `verified` (~238 tokens)

Verified best price + a SHAREABLE signed proof — the one call that both prices an item AND gives you something to SHOW. Returns the genuine best price across real sellers PLUS an Ed25519-signed attestation written to AgentsPrice's public transparency log, AND two public, no-key URLs you can hand to your user or embed anywhere: verify_url (a human-readable proof page) and badge_url (a '✓ Verified best price' badge image). It also returns a ready-to-paste `embed` HTML snippet. Use this whenever you surface a price to a person or another agent and want them to trust it WITHOUT trusting you — link the verify_url or drop in the badge. Prices are real or an honest 'unavailable' — a proof is only ever issued over a price we actually verified, never a fabricated one. Categories: electronics, gaming, home, fashion, crypto, all. Needs an AgentsPrice API key (call get_free_key) — or pay per call via x402 (see /.well-known/x402).

Input parameters:

- `api_key` (string)
- `category` (string)
- `item` (string, required)

### `referral_status` (~134 tokens)

Your AgentsPrice referral standing: your shareable referral code + link, how many agents signed up through it, how many have CONVERTED (actually paid), and your resulting bonus calls/month. The reward is +1,000 calls/month per conversion, additive to your plan ceiling and permanent — earned only when a referred agent actually pays (upgrade or pay-per-call), never on signup. Share your link (https://agentsprice.com/?ref=<your_code>) wherever you onboard other agents; pass that code as get_free_key(referred_by=...). Needs your AgentsPrice API key.

Input parameters:

- `api_key` (string)

### `price_lock` (~205 tokens)

Freeze a VERIFIED price as a STABLE, signed reference for a window (default 300s, max 86400) so you can run a multi-step plan — budget check, approval, negotiation, checkout — against ONE number that won't move under you mid-flight. Returns a lock_id + Ed25519-signed terms appended to the public transparency log, plus redeem + status URLs. Honest scope, bound into the signature: AgentsPrice HOLDS this observed price as a stable reference until it expires — NOT a guarantee the seller or market price holds, that the item is in stock, or that a transaction will succeed. Only ever issued over a price we actually verified. Redeem within the window via redeem_lock(lock_id). Needs an AgentsPrice API key (call get_free_key) — or pay per call via x402.

Input parameters:

- `api_key` (string)
- `category` (string)
- `item` (string, required)
- `ttl_seconds` (integer)

### `redeem_lock` (~124 tokens)

Redeem an active price lock within its window (one created by price_lock). Pass the redeem_token that price_lock returned to you — the lock_id alone is PUBLIC (it appears in the transparency log) and does not authorise redemption, so without the token anyone could consume your lock. Records + signs a redemption in the public transparency log and returns the settlement. Idempotent — a second redeem is a safe no-op. Remember a lock is a stable signed reference, not a seller guarantee.

Input parameters:

- `lock_id` (string, required)
- `redeem_token` (string)

### `budget_guard` (~214 tokens)

Before you SPEND, get a SIGNED allow / deny / escalate verdict your principal can trust. AgentsPrice compares your proposed_price to the verified live market and applies your policy (max_over_market_pct; optional hard_ceiling), returning the verdict PLUS an Ed25519-signed record in the public transparency log — so an owner/treasury can let you spend autonomously knowing every payment carries a third-party "this was within policy at market" receipt. 'deny' if over policy; 'escalate' when no verified market price exists (we never fake a pass). Honest scope, bound into the signature: a price check, NOT advice the purchase is wise. Needs an AgentsPrice API key (call get_free_key) — or pay per call via x402.

Input parameters:

- `api_key` (string)
- `category` (string)
- `hard_ceiling` (number)
- `item` (string, required)
- `max_over_market_pct` (number)
- `proposed_price` (number, required)

### `settle` (~214 tokens)

Settle a dispute over a prior AgentsPrice attestation. Pass the transparency-log `seq` (or `attestation_id`) of a signed price/lock/verdict, and AgentsPrice reads it back out of its OWN append-only log and returns a SIGNED ruling — upheld / overturned / indeterminate. 'overturned' if the record was retracted, its signature doesn't validate, or (when you pass claim_price) a counterparty's claimed price doesn't match what we actually attested. This is the neutral clearinghouse: an escrow or contract can release/withhold on a ruling neither side can rewrite. Honest scope, bound into the signature: it rules only on what AgentsPrice attested and whether it stands — not on the transaction or the seller. Needs an AgentsPrice API key (call get_free_key) — or pay per call via x402.

Input parameters:

- `api_key` (string)
- `attestation_id` (string)
- `claim_price` (number)
- `seq` (integer)

## Diagnostics

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

## Score history

- 2026-08-03: 20
- 2026-08-02: 62
- 2026-08-01: 62
- 2026-07-31: 61
- 2026-07-30: 58
- 2026-07-29: 58
- 2026-07-28: 57
- 2026-07-27: 45
- 2026-07-26: 56

## Links

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