# Codex vs CryptoQuant MCP server (slim)

> Codex scores 75.4 (BB) to CryptoQuant's 51.7 (D) for crypto market data. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/codex-graphql-vs-cryptoquant-mcp.md (~4,550 tokens) · this version ~2,880 tokens · JSON https://www.anchorterminal.com/compare/codex-graphql-vs-cryptoquant-mcp.json · canonical https://www.anchorterminal.com/compare/codex-graphql-vs-cryptoquant-mcp
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Codex scores 75.4 (BB) on agent readiness against CryptoQuant MCP server's 51.7 (D), and leads in 6 of 7 scored categories. Both do crypto market data.

- Codex: BB 75.4, rank #64 of 1486 · https://www.anchorterminal.com/tools/codex-graphql.min.md
- CryptoQuant MCP server: D 51.7, rank #1009 of 1486 · https://www.anchorterminal.com/tools/cryptoquant-mcp.min.md
- Codex, good for On-chain token prices, charts, holders, wallet PnL, launchpad streams and Polymarket and Kalshi data for trading agents and crypto apps. Ahead on Reliability, 85 against 45; Schema & documentation, 91 against 64; Agent ergonomics, 79 against 65; Payments & pricing, 80 against 40; Maintenance & community, 80 against 70. Also Agent-ready, a grade of BB or better; No incidents deducted, where CryptoQuant MCP server loses 3 points for them.
- CryptoQuant MCP server, good for Agents answering questions about Bitcoin and Ethereum on-chain flows, valuation indicators and derivatives, for users on Professional or Premium. Also Runs on your own machine.

| Category | Codex | CryptoQuant MCP server |
| --- | --- | --- |
| Reliability (16%) | 85 | 45 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 91 | 64 |
| Agent ergonomics (13%) | 79 | 65 |
| Security & auth (14%) | 49 | 48 |
| Payments & pricing (10%) | 80 | 40 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 80 | 70 |
| Transparency & trust (7%) | 59 | 59 |

| Fact (where they differ) | Codex | CryptoQuant MCP server |
| --- | --- | --- |
| Kind | HTTP API | MCP server |
| Vendor | Codex Data Inc. | Team CQ Inc. (CryptoQuant) |
| Hosted endpoint | `https://graph.codex.io/graphql` | `https://mcp.cryptoquant.com/mcp` |
| Transports | HTTP, websocket | Streamable HTTP, stdio |
| Auth | API key | OAuth or key |
| Licence | Proprietary service under Codex Data Inc.'s terms of service. The TypeScript SDK is MIT | The npm stdio proxy, plugin manifest and skill are MIT. The remote server at mcp.cryptoquant.com is closed and runs under CryptoQuant's Terms of Service, which sit behind a bot check and weren't read |
| Tools exposed | 0 | 9 |
| Read-only variant documented | no | yes |
| MCP registry | not listed | `com.cryptoquant/mcp-server` |
| Last release | 2026-11-02 | 2026-10-02 |
| Terms last updated | 2026-10-29 | couldn't be read |
| Privacy policy last updated | 2026-09-29 | couldn't be read |
| Customer content may train models | not found in the text | couldn't be read |
| Terms restrict automated access | yes | couldn't be read |
| Terms restrict benchmarking | not found in the text | couldn't be read |
| Terms or service can change without notice | yes | couldn't be read |
| Arbitration or class-action waiver | yes | couldn't be read |
| Popularity | 75k npm/wk | 49 npm/wk |
| Agent reviews | none | 3.5/5 (4) |

Why the edge:
- Reliability, Codex +40: Codex 85 (Hosted lines. Status page at status.codex.io (incident.io) with API, Dashboard and 25 network components and a history page (20). The history from 8 August to 6 November lists an elevated-latency incident on 11 August (balances queries, 42 minutes, labelled degraded performance), a 5xx spike the same day, degraded filterTokens on 12 August, and network delays on Robinhood, BNB, Cronos, Fogo and Solana pricing in late August and September, with none in October or November. All read as partial or degraded, so minor only (20). Per-plan rate limits (5 a second free, 300 on Growth with a 500 burst) and per-request maxima are published (15). 429 TOO_MANY_REQUESTS carries `retryAfterSeconds` and `Retry-After`, OVER_CAPACITY says to wait 30 seconds, and the errors page says which codes to retry; writes are limited to webhook and token mutations (15). The pricing page shows '99.9% Uptime SLA' as a headline figure and custom SLAs on Enterprise, with no SLA document found (5 of 10). The API is generally available (10). 20+20+15+15+5+10 = 85.); CryptoQuant MCP server 45 (Graded with the hosted lines, on the remote server. No status page covers the MCP server. status.cryptoquant.com, titled "CryptoQuant API Status", is CryptoQuant's own monitor of data freshness for 695 API endpoint windows, with error history from 31 August 2026, but no page reviewed links to it. Judgement call, 10 of 20. Its record shows 118 grouped events, nearly all late data rather than errors, including 32 XRP endpoints stale for about 7 hours on 26 September and 47 BTC endpoints for about 2 hours on 16 September. Several multi-hour delays on parts of the data, none a full outage (10 of 30). Rate limits are published per plan, 10, 60, 120 and 800 requests a minute, but the keyless pool has no figure (12 of 15). 429 means back off and retry after a short delay, and 402 means the credits are spent; no Retry-After or backoff figure is documented. All tools read data, so safe retries matter less (8 of 15). No SLA found on any plan; the terms couldn't be read (0). The npm package and registry entry are 1.0.0, but the MCP guide and the user guide both carry a beta notice on 24 October (5 of 10).)
- Payments & pricing, Codex +40: Codex 80 (MPP (Machine Payments Protocol) on every query endpoint, paid in USDC on Tempo; subscriptions and webhooks are not covered, and it is not x402 (35 of 40). $0.001 a query through MPP, compute-unit costs per operation, and Growth at $120 per million compute units, all public (20). The Almost free plan's 10,000 compute units need a one-time $1 activation fee by card or 1 USDC, which the terms say confirms a payment method (5 of 20). An agent can pay per query with no account or key (20). 35+20+5+20 = 80.); CryptoQuant MCP server 40 (No x402, MPP or L402 (0). Plan prices and the top-up price, $5 per 100,000 credits, are public without a login, but credits per call vary with rows and data type and no per-call figure is published (10 of 20). Keyless MCP use needs no account and no card, and Basic is free with 10,000 credits a month (20). An MCP client can register itself by dynamic client registration and use keyless, but someone still clicks "Continue with Keyless" on a sign-in page that loads Cloudflare Turnstile; there's no programmatic key API (10 of 20).)
- Schema & documentation, Codex +27: Codex 91 (The full GraphQL schema, 18,159 lines, is in the MIT SDK repository at src/resources/schema.graphql, updated on 5 November 2026, and introspection is free (25). llms.txt, llms-full.txt and a Markdown twin of every page (10). Reference pages give a one-line purpose per operation, and the API reference intro, the queries-versus-subscriptions page and llms.txt say which operation to use for which job and to batch rather than loop (13 of 20). GraphQL types with enums, input objects and non-null markers, and documented maxima per argument (14 of 15). Examples on every recipe and reference page, and an error table with code, HTTP status, meaning and retry advice (14 of 15). Weekly dated changelog from 26 August 2024 to 2 November 2026 with RSS and dated deprecations (15). 25+10+13+14+14+15 = 91.); CryptoQuant MCP server 64 (The remote server's tool schemas aren't public, because `tools/list` answers 401 without a token and no manifest was found. The REST API behind it has OpenAPI 3.0 for v1 (242 endpoints), an OpenAPI file for v2 and a machine-readable metric catalogue (15 of 25). llms.txt, llms-full.txt and Markdown for every docs page (10). The `cryptoquant-onchain` skill says when to use the tools, the order to call them, a question-to-metric map and what to do with plan notices; the tool descriptions themselves weren't readable (12 of 20). Input types are unseen, and the skill describes `query_data(endpoint, params)` with endpoint-specific parameters found through `get_endpoint_info`, which suggests a free parameter map (5 of 15). The API docs give request and response examples and a full status-code table; MCP-level errors aren't documented (10 of 15). The repository has a Keep a Changelog file with 1.0.0's breaking changes and a migration section, and the API has a dated changelog, but changes to the remote server's tools aren't logged anywhere (12 of 15).)
- Agent ergonomics, Codex +14: Codex 79 (GraphQL field selection, so a response holds only the fields asked for, and `usageData` reports the cost of a request (23 of 25). `limit` on filter queries up to 200, rankings and 100+ filter signals on filterTokens; some list arguments drop extra inputs silently rather than failing (18 of 20). Coded errors an agent can branch on, but most arrive as HTTP 200 in an `errors` array, and an inline input type mismatch returns only a message (16 of 20). Queries are reads and identical requests cost the same; errors are not billed except NOT_FOUND. No idempotency key on the webhook and token mutations (14 of 20). Few required arguments beyond `networkId`. One official SDK, TypeScript (8 of 15). 23+18+16+14+8 = 79.); CryptoQuant MCP server 65 (Graded on the remote server from the README and skill, since the definitions couldn't be read. Nine tools, with endpoints found through `discover_endpoints` and `get_endpoint_info` so the 245 or so metrics stay out of context. Compactness unchecked (22 of 25). The API takes `window`, `from`, `to` and `limit`, and the skill gives the date formats; how far `query_data` exposes them wasn't checked (14 of 20). The API's errors carry a code and type (`bad_request`, `payment_required`, `forbidden`, `too_many_requests`), and the skill says plan notices come back with an upgrade link. MCP error shapes aren't documented (12 of 20). Every tool reads data and failed calls aren't charged, so retries are safe, but readOnlyHint and other annotations couldn't be checked (10 of 20). Few required parameters per the skill, but no official SDK; the docs show Python and JavaScript snippets only (7 of 15).)
- Maintenance & community, Codex +10: Codex 80 (Closed service. Newest changelog entry 2 November 2026 (30). Weekly entries from 3 August to 2 November, and SDK releases 2.5.10 to 2.5.20 between 28 October and 5 November (20). Public changelog, a Discord, a support address and a status page with a report link; GitHub issue replies were not sampled (10 of 15). Current official TypeScript SDK, no other languages (12 of 15). The SDK repository runs lint and test on pull requests and a release workflow (8 of 10). 30+20+10+12+8 = 80.); CryptoQuant MCP server 70 (npm 1.0.0 on 2 October 2026, registry entry on 7 October, API changelog entry on 23 October (30). The MCP package had one release in 90 days (1.0.0); the registry's earlier 0.1.1 is from 8 June. The API changelog has six dated entries since 19 August. 10 of 20, a judgement call between the two. A public changelog and an Intercom help centre. Issue and pull-request response times couldn't be read; the five pull requests in git history are maintainers' own, merged on 2 and 6 October (8 of 25). Listed in the official MCP registry under the verified namespace com.cryptoquant (15). npm publishing uses Trusted Publishing with provenance, builds and runs vitest on release, and depends on @modelcontextprotocol/sdk ^1.31.0; there's no CI on pushes or pull requests (7 of 10).)