# X MCP vs Xpoz MCP (slim)

> X MCP scores 53.1 (D) to Xpoz MCP's 39.6 (E) for social analytics. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/x-mcp-vs-xpoz-mcp.md (~4,250 tokens) · this version ~2,480 tokens · JSON https://www.anchorterminal.com/compare/x-mcp-vs-xpoz-mcp.json · canonical https://www.anchorterminal.com/compare/x-mcp-vs-xpoz-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)

X MCP scores 53.1 (D) on agent readiness against Xpoz MCP's 39.6 (E), and leads in 5 of 7 scored categories. Xpoz MCP leads on agent ergonomics and payments & pricing. Both do social analytics.

- X MCP: D 53.1, rank #967 of 1510 · https://www.anchorterminal.com/tools/x-mcp.min.md
- Xpoz MCP: E 39.6, rank #1339 of 1510 · https://www.anchorterminal.com/tools/xpoz-mcp.min.md
- X MCP, good for Research and monitoring on X by an agent whose owner already has, or will pay for, an X developer app, such as searching the archive, reading timelines and mentions, and filing bookmarks. Ahead on Reliability, 72 against 20; Maintenance & community, 70 against 25; Transparency & trust, 59 against 29. Also Runs on your own machine.
- Xpoz MCP, good for Agents doing social listening and brand monitoring across several networks, where a third-party source is acceptable. Ahead on Agent ergonomics, 63 against 45; Payments & pricing, 30 against 20.

| Category | X MCP | Xpoz MCP |
| --- | --- | --- |
| Reliability (16%) | 72 | 20 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 65 | 64 |
| Agent ergonomics (13%) | 45 | 63 |
| Security & auth (14%) | 40 | 37 |
| Payments & pricing (10%) | 20 | 30 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 70 | 25 |
| Transparency & trust (7%) | 59 | 29 |

| Fact (where they differ) | X MCP | Xpoz MCP |
| --- | --- | --- |
| Vendor | X Corp. | XPOZ |
| Hosted endpoint | `https://api.x.com/mcp` | `https://mcp.xpoz.ai/mcp` |
| Transports | Streamable HTTP, stdio | Streamable HTTP |
| Auth | OAuth or key | API key |
| Pricing | Pay per use | Freemium |
| Licence | Proprietary hosted server under the X Developer Agreement. The xurl bridge on GitHub and npm is MIT | none |
| Tools exposed | none | 52 |
| llms.txt | yes | no |
| MCP registry | not listed | `ai.xpoz/social-insights` |
| Last release | 2026-09-29 | none |
| Terms last updated | 2026-04-27 | not read yet |
| Privacy policy last updated | couldn't be read | no document linked |
| Customer content may train models | not found in the text | not read yet |
| Terms restrict automated access | not found in the text | not read yet |
| Terms restrict benchmarking | yes | not read yet |
| Terms or service can change without notice | not found in the text | not read yet |
| Arbitration or class-action waiver | yes | not read yet |
| Popularity | 1.4k stars, 6k npm/wk | none |

Why the edge:
- Reliability, X MCP +52: X MCP 72 (Read with the hosted lines, since the server runs at api.x.com and the bridge only relays. docs.x.com and developer.x.com are separate hosts with open robots.txt files. The incident history was re-read on 4 November, and the other lines are per the 8 October check, not re-read. A status page exists at developer.x.com/status but needs JavaScript and showed our reader nothing. The dated incident history at docs.x.com/incidents.md lists incidents by title, with no component view and no MCP entry (15 of 20, an earlier partial kept). On 4 November that history still has no incident dated after 1 July 2026, apart from a 'Missing entities.annotations' entry marked ongoing since 24 March 2026, so the earlier partial stays, as the x-ads listing holds it on the same page (25 of 30). API rate limits are published per endpoint, such as 300 per 15 minutes and 1 a second for full-archive search and 50 per 15 minutes for bookmark writes. The MCP page gives no numbers of its own and says only that writes are stricter than reads (12 of 15, an earlier partial kept). 429s come with `x-rate-limit-reset` and the docs advise waiting for it and backing off. No Retry-After and no idempotency keys or safe-retry guidance for writes were found, so backoff alone (10). No SLA found for Pay-per-use (0). The MCP page carries no beta or preview label (10). 15+25+12+10+0+10 = 72.); Xpoz MCP 20 (No status page found (0). No history (5). Credit allowances, no rate limits found (5 of 15). No retry guidance (0). No SLA (0). Not labelled beta (10). 0 + 5 + 5 + 0 + 0 + 10 = 20.)
- Maintenance & community, X MCP +45: X MCP 70 (X's platform changelog (re-read on 4 November) has an X API v2 entry dated 26 October 2026 (Direct Message refusal error details), 9 days before 4 November, and the xurl bridge's newest release is 1.3.4 on 29 September 2026 (30). In the 90 days from 6 August the changelog dates six X API v2 entries, on 1 September (documented media limits), 21 September (OAuth 1.0a to 2.0 token exchange), 29 September (broadcast chat removal events), 1 October (a rewritten guide), 2 October (free credit incentives) and 26 October. Ads API entries are left to the x-ads listing. xurl tagged 1.3.2 (24 September, a Homebrew cask fix, packaging-only, half), 1.3.3 (29 September, an `xurl chat add-members` fix, full) and 1.3.4 (29 September, republishing 1.3.3's binaries and npm package, packaging-only, half). Well over three dated entries (20). The xmcp repository has no tags and no commit since 9 April 2026. The xurl changelog credits fixes to numbered issues. Issue threads couldn't be read (GitHub's pages answer 403) and the developer forum's robots.txt closes it to us (12 of 25, an earlier partial kept). The registry line's readings on 8 October and 4 November both came from the official MCP registry's JSON search API, which this run doesn't use, so they are struck and no registry entry is established (0). Go 1.24 with build, test, gofmt and release-build jobs in CI, results unread (8 of 10). 30+20+12+0+8 = 70.); Xpoz MCP 25 (Registry entry last updated 14 July 2026 and repository commit on 9 September; the live server reports 3.0.0 (10). No dated releases in 90 days (0). Issues not read (0). Official registry entry ai.xpoz/social-insights (15). Docker packaging only (0). 10 + 0 + 0 + 15 + 0 = 25. Registry presence read from Anchor Terminal's own daily import of the official MCP registry (/api/v1/registry.json, 6 November 2026), not the registry's API.)
- Transparency & trust, X MCP +30: X MCP 59 (Editorial half only. The hosted server is closed, under a Developer Agreement last updated 27 April 2026, and the bridge is MIT per the xurl LICENSE read on 4 November (18 of 30, an earlier partial kept). The 8 October data-handling reading came from X's privacy policy and terms of service on x.com, whose robots.txt disallows every path for unnamed agents, so it is struck. The Developer Agreement (re-read on 4 November) links a controller-to-controller data protection addendum on gdpr.x.com, which wasn't read, and no retention statement or subprocessor list for developers was found in the pages still readable (0 of 30). The versioning page (re-read on 4 November) limits breaking changes to major versions, at most yearly, with migration guides, and says a deprecated version works for 'a defined period' without stating one. Dated notices exist but can be short, such as five days for the Account Activity replay endpoint in March 2026 and four days for the removal of follows, likes and quote posts from self-serve tiers in April 2026. Dated notices with no stated period take this run's settled 15 (15 of 20, from 14). The controller names came from the struck privacy policy, and no subprocessor or data location list was found (0 of 20). 18+0+15+0 = 33.); Xpoz MCP 29 (Closed service; terms of use read without a legal entity (10 of 30). Data handling not read (5 of 30). No deprecation policy (0). Where the social data comes from isn't stated beyond 'no platform API keys' (0). 10 + 5 + 0 + 0 = 15.)
- Agent ergonomics, Xpoz MCP +18: X MCP 45 (Per the 8 October check, not re-read on 4 November, apart from the xurl clone and the MCP page. The number of tools isn't published. One docs page lists six groups and another says XMCP exposes 200+ endpoints as tools, so context cost is not established (5 of 25). The API has `max_results`, `pagination_token`, field selection and expansions. Whether each MCP tool passes them through is unread (12 of 20). Errors are problem+json with a type URI, title and detail, and the xurl CHANGELOG (1.2.0) says the bridge turns transport and token failures into JSON-RPC errors keyed to the request (15 of 20). No idempotency keys, and no readOnlyHint or destructiveHint documented. The bridge refreshes the token and retries after a 401 (4 of 20). One npx line starts the bridge and the URL has a default, but each user first creates an app, registers a redirect URI and sets a 300-second startup timeout. Official XDKs exist for Python and TypeScript (9 of 15). 5+12+15+4+9 = 45.); Xpoz MCP 63 (52 tools totalling about 238 KB (5). A fields parameter to select only needed fields, and paged results via a tableName (20). No documented errors (3 of 20). All annotated, 49 read-only (20). SDKs and a CLI (15). 5 + 20 + 3 + 20 + 15 = 63.)
- Payments & pricing, Xpoz MCP +10: X MCP 20 (Per the 8 October check, not re-read on 4 November. No x402, MPP or L402 (0). Per-resource and per-request prices are published without a login, such as $0.005 a post read, $0.010 a user read and $0.005 a bookmark write (20). No free tier. Credits are bought in advance, and the one-time $20 credit needs a saved payment card (0). A person signs in to the developer portal, creates an app and completes a browser login (0). 0+20+0+0 = 20.); Xpoz MCP 30 (No machine payment protocol (0). Plan prices public (10). Free 500 credits (20). A person signs in for a key (0). 0 + 10 + 20 + 0 = 30.)