Oakallow
A hosted governance checkpoint that sits between your AI agent and the tools it wants to call. Instead of letting the agent execute directly, you route risky actions through Oakallow's approval flow: the agent calls check_permission or request_approval, a human decides in the dashboard under MFA, and Oakallow mints a single-use signed token if approved. Every execution gets logged to an immutable audit trail. Connects over streamable HTTP with OAuth 2.1. You'd reach for this when you want agents to investigate and recommend, but need a human gate before they actually change state in production systems. Includes preflight resources to check session status and billing before committing to the approval flow.
- GitHub stars
- 1
- tools
- 4
- transport
- HTTP
- last updated
- Oct 23, 2026
Tools
4 toolsPublic tool metadata for what this MCP can expose to an agent.
list_my_toolsEnumerate the tools available to the signed-in user in the named org (`org` arg; see below)
Enumerate the tools available to the signed-in user in the named org (`org` arg; see below)
No parameter schema in public metadata yet.
check_permissionAsk whether a given tool call would be allowed, require approval, or be blocked (takes an `org` arg; see below)
Ask whether a given tool call would be allowed, require approval, or be blocked (takes an `org` arg; see below)
No parameter schema in public metadata yet.
list_pending_approvalsList approval requests still awaiting a human decision
List approval requests still awaiting a human decision
No parameter schema in public metadata yet.
check_approval_statusPoll a pending approval request by reference number
Poll a pending approval request by reference number
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Oakallow MCP Server
Runtime permission, approval, and audit governance for AI agent tool execution.
Oakallow is a hosted remote MCP server. It sits between an agent and the actions it wants to take, so that a specific action can be checked, gated behind human approval when it is risky, authorized with a single-use signed token, and recorded in an immutable audit log, at the moment of execution.
- Website: https://oakallow.com
- MCP endpoint:
https://api.oakallow.io/mcp(Streamable HTTP) - OAuth 2.1 compliance: https://oakallow.com/docs/oauth
- MCP protocol details: https://oakallow.com/docs/mcp
What this connector is for
Details
- Repository
- github.com/oakallow/oakallow-mcp
- Website
- oakallow.com
- Category
- AI & LLM Tools
- Transport
- HTTP
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Ygoprodeckpipeworx-io/mcp-ygoprodeckYGOPRODeck MCP — Yu-Gi-Oh! trading card game (TCG) database. Keyless. Sends a User-Agent. Base…1stars
Skillflowrafsilva85/skillflow-mcp-serverSearch, discover, and install 500+ AI agent skills from the SkillFlow marketplace.1stars
Tentra — Memory for AI Coding Agentsrdanieli/tentra-mcpMemory for AI coding agents. Call graphs + refactor safety + persistent code context. 35 MCP tools.1stars
Mcp Serverrotifer-protocol/rotifer-mcp-serverSearch, compare, and install self-evolving AI Agent Genes ranked by Arena fitness1stars
Serper Search MCPsmjahid012/serper-search-mcp-serverUniversal Google Search MCP: web, images, places, shopping, scholar, patents, deep research & RAG1stars
Rhumb Mcpsupertrained/rhumbAgent gateway for Index discovery, AN Score evaluation, and Resolve governed execution1stars