MCP server

drift — mandate enforcement for AI agents

io.github.mrpkk/drift

Checked 25 Oct 2026, 20:29 UTC · Connected to it and listed its tools

Block an action a signed mandate does not permit: amount, payee, audience, currency, window, intent.

Working at last checkAbout 1,231 tokens per request once connected3 tools

https://drift.rta.lat/mcp

At a glance

Type: MCP server
Publisher: Not verified
Status: Working at last check
Tools: 3
Token cost: About 1,231 tokens per request
Sets up in: Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok
Last checked: 25 Oct 2026, 20:29 UTC

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http drift https://drift.rta.lat/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.drift]
url = "https://drift.rta.lat/mcp"

Gemini CLI

{"mcpServers":{"drift":{"httpUrl":"https://drift.rta.lat/mcp"}}}

Cursor

{"mcpServers":{"drift":{"url":"https://drift.rta.lat/mcp"}}}

VS Code

{"servers":{"drift":{"type":"http","url":"https://drift.rta.lat/mcp"}}}

Antigravity

agy mcp add drift https://drift.rta.lat/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"drift","server_url":"https://drift.rta.lat/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"drift","server_url":"https://drift.rta.lat/mcp"}

drift_check ~783 tokens
Check ONE proposed action against a signed agent mandate BEFORE it happens. Returns {"verdict": "ALLOW"|"DENY", "rule": <name>} plus a report with a ledger fingerprint. Six rules run in a fixed order, so a refusal names the most important reason rather than an incidental one: amount, payee, audienc
drift_explain ~183 tokens
Return the six enforcement rules in the exact order they are applied, each with a plain-language reason it exists. Takes no mandate and no action. Use when a refusal did not make sense, or before explaining a denial to someone whose mandate was rejected. A refusal you cannot explain is one nobody w
drift_session ~265 tokens
Check a SEQUENCE of proposed actions against one mandate. Returns {submitted, allowed, denied, breach_by_rule, fingerprint}. Use for a whole plan or batch, not a single action — use drift_check for that. The fingerprint is the point: rewriting or reordering any earlier decision changes the hash, so

HANRIA agent mandate check
Check an agent action against its operator's mandate before acting: permit, deny or escalate.
Kya Brasil
KYA backed by a real company: e-CNPJ-signed agent mandates, revocation-checked, signed verdicts
Helena Good: Scientific Infrastructure Sponsorship
Fund or spread Helena's public scientific infrastructure to keep it free to use and independent.
Rokha
Search a registry of agent skills and MCP servers, then run them for real. No install, traced.
Worldcastr Remote MCP
Built-environment forecasts, public benchmarks, and permit or zoning readiness through remote MCP.
Agent Transaction Control
Issue Agent Passports and verify agent authority before value moves. Signed verification records.
Sunaiva Gate — Agent Rule Enforcement
MCP enforcement layer that intercepts AI agent actions and blocks rule violations before execution.
movahedi.ca Privacy Data
Canadian privacy enforcement, glossary, and Quebec Law 25 guidance for AI agents.

[![AptLynx](https://aptlynx.net/badge/io.github.mrpkk/drift.svg)](https://aptlynx.net/servers/io.github.mrpkk/drift)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents