io.github.IvanBBaev/x-mcp-ai

io.github.IvanBBaev/x-mcp-aiv0.8.0Other

Safety-first X (Twitter) API v2 MCP server: 41 typed tools across 12 packages, policy-gated.

The current version, v0.8.0, was published to the official MCP registry on 2026-08-29. It is distributed as x-mcp-ai on npm, filed under Other by this index, and declares 18 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; the index's current counts put this record in context.

In-path gate · all MCP tools

Using io.github.IvanBBaev/x-mcp-ai in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire

Auditable install path →Watch it hold a drift →

Trust verdict · v1 advisory · method

NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

That verdict was true at screening time (snapshot 2026-08-30).

Contracts can change after screening, with no version bump. The gate pins io.github.IvanBBaev/x-mcp-ai’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Environment variables

X_MCP_AUTH_MODE

Authentication mode: oauth2 (default) or app-only.

X_MCP_CLIENT_ID

OAuth 2.0 client ID (oauth2 mode).

X_MCP_CLIENT_SECRET

secret

OAuth 2.0 client secret (confidential clients only).

X_MCP_BEARER_TOKEN

secret

Application-only bearer token (app-only mode).

X_MCP_TOKEN_FILE

Path to the rotating OAuth 2.0 token store (default: OS-resolved).

X_MCP_TOKEN_KEYCHAIN

Set to 1 to keep OAuth 2.0 tokens in the OS keychain (macOS, Linux) instead of a token file. Mutually exclusive with an explicit X_MCP_TOKEN_FILE.

X_MCP_POLICY

Policy preset: read-only (default), engage, publish, manage, or full.

X_MCP_POLICY_ALLOW

Comma-separated op:domain cells to allow on top of the preset (e.g. read:dm,write:dm).

X_MCP_POLICY_DENY

Comma-separated op:domain cells to deny; deny beats allow beats preset.

X_MCP_HIDE_DENIED

Set to 1 to drop policy-denied tools from registration entirely instead of registering them annotated as denied.

X_MCP_MEDIA_DIR

Directory uploads must resolve inside. Media upload is disabled unless this is set.

X_MCP_AVAILABILITY

Comma-separated specially-provisioned access classes to declare: pilot, premium-user, enterprise. Unset means the conservative default (app+user, user-only).

X_MCP_PROFILES_FILE

Path to a profiles file holding named configuration blocks.

X_MCP_PROFILE

Name of the profile to select from the profiles file.

X_MCP_TIMEOUT_MS

Per-HTTP-request timeout in milliseconds (default 30000).

X_MCP_LOG_LEVEL

Diagnostic verbosity on stderr: silent, error, info (default), or debug.

X_MCP_CREDIT_BUDGET

Session spend cap in USD.

X_MCP_BUDGET_MODE

Budget enforcement: warn (default) or hard.

MCP quality score · maturity, not trust · methodology

freshness

completeness

installability

documentation

stability

Alternatives in Other

AgentRoam

ai.agentroam/agentroam

Buy travel eSIMs, gift cards and mobile top-ups with crypto — user confirms before any order.

Authoryze

ai.authoryze/authoryze

Give your AI agent a spending limit: approval controls and single-use virtual cards.

io.github.IvanRublev/keyphrases-mcp

An MCP server to extract keyphrases from a text with the BERT model

Install this server

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "x-mcp-ai": {
      "command": "npx",
      "args": [
        "-y",
        "--",
        "x-mcp-ai"
      ],
      "env": {
        "X_MCP_AUTH_MODE": "<x_mcp_auth_mode>",
        "X_MCP_CLIENT_ID": "<x_mcp_client_id>",
        "X_MCP_CLIENT_SECRET": "<your-x_mcp_client_secret>",
        "X_MCP_BEARER_TOKEN": "<your-x_mcp_bearer_token>",
        "X_MCP_TOKEN_FILE": "<x_mcp_token_file>",
        "X_MCP_TOKEN_KEYCHAIN": "<x_mcp_token_keychain>",
        "X_MCP_POLICY": "<x_mcp_policy>",
        "X_MCP_POLICY_ALLOW": "<x_mcp_policy_allow>",
        "X_MCP_POLICY_DENY": "<x_mcp_policy_deny>",
        "X_MCP_HIDE_DENIED": "<x_mcp_hide_denied>",
        "X_MCP_MEDIA_DIR": "<x_mcp_media_dir>",
        "X_MCP_AVAILABILITY": "<x_mcp_availability>",
        "X_MCP_PROFILES_FILE": "<x_mcp_profiles_file>",
        "X_MCP_PROFILE": "<x_mcp_profile>",
        "X_MCP_TIMEOUT_MS": "<x_mcp_timeout_ms>",
        "X_MCP_LOG_LEVEL": "<x_mcp_log_level>",
        "X_MCP_CREDIT_BUDGET": "<x_mcp_credit_budget>",
        "X_MCP_BUDGET_MODE": "<x_mcp_budget_mode>"
      }
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "x-mcp-ai": {
      "command": "npx",
      "args": [
        "-y",
        "--",
        "x-mcp-ai"
      ],
      "env": {
        "X_MCP_AUTH_MODE": "<x_mcp_auth_mode>",
        "X_MCP_CLIENT_ID": "<x_mcp_client_id>",
        "X_MCP_CLIENT_SECRET": "<your-x_mcp_client_secret>",
        "X_MCP_BEARER_TOKEN": "<your-x_mcp_bearer_token>",
        "X_MCP_TOKEN_FILE": "<x_mcp_token_file>",
        "X_MCP_TOKEN_KEYCHAIN": "<x_mcp_token_keychain>",
        "X_MCP_POLICY": "<x_mcp_policy>",
        "X_MCP_POLICY_ALLOW": "<x_mcp_policy_allow>",
        "X_MCP_POLICY_DENY": "<x_mcp_policy_deny>",
        "X_MCP_HIDE_DENIED": "<x_mcp_hide_denied>",
        "X_MCP_MEDIA_DIR": "<x_mcp_media_dir>",
        "X_MCP_AVAILABILITY": "<x_mcp_availability>",
        "X_MCP_PROFILES_FILE": "<x_mcp_profiles_file>",
        "X_MCP_PROFILE": "<x_mcp_profile>",
        "X_MCP_TIMEOUT_MS": "<x_mcp_timeout_ms>",
        "X_MCP_LOG_LEVEL": "<x_mcp_log_level>",
        "X_MCP_CREDIT_BUDGET": "<x_mcp_credit_budget>",
        "X_MCP_BUDGET_MODE": "<x_mcp_budget_mode>"
      }
    }
  }
}

Cline (cline_mcp_settings.json)

npx -y -- x-mcp-ai

Claude Code (claude mcp add)

claude mcp add --scope user x-mcp-ai -- npx -y -- x-mcp-ai

Gemini CLI (gemini mcp add)

gemini mcp add -s user x-mcp-ai npx -y -- x-mcp-ai

Verdict API

curl -s mcpindex.ai/api/v1/trust/server/io-github-ivanbbaev-x-mcp-ai

Free-tier verdict as JSON: decision + dimensions + severity. Call it from your agent before it invokes a tool it just discovered.

Details

version: v0.8.0
category: Other
quality: 80 / 100
operator: IvanBBaev

Listing

Listed from the official MCP registry. Unclaimed by its maintainer. Maintainer? Email us →

Provenance

Each verdict is bound to a hash of the exact description it judged, so a re-crawl that changes the text produces a new record rather than silently inheriting this one. Verdict history is hash-chained and anchored to Bitcoin via OpenTimestamps (latest confirmed at block 964,530). Verify it yourself.

Links

Repository →