Oakallow MCP server
Commit Oct 23, 2026Provides a governance layer for AI agents to request human approval, check permissions, and maintain immutable audit logs for tool execution.
Also known as oakallow/oakallow-mcp, oakallow-mcp
- Stars
- 1
- Tools
- 6
- Downloads, 30 days
- —
- Latest version
- 1.1.0
- Last commit
- Oct 23, 2026
- License
- MIT
What is Oakallow MCP?
Oakallow provides a governance layer for AI agents to request human approval, check permissions, and maintain immutable audit logs for tool execution. It exposes 6 tools, such as list_my_tools, check_permission, list_pending_approvals.
Summary generated from the project's README
About Oakallow MCP server
Oakallow acts as a governance layer for AI agents, sitting between an agent and its intended actions to ensure security and accountability. It provides a mechanism for agents to request human approval for risky tasks, verify permissions, and maintain an immutable audit log of all tool executions. This hosted remote server is designed for developers building autonomous or semi-autonomous agents that require oversight through multi-factor authentication via a dashboard or mobile app.
Users connect to the service using either interactive OAuth 2.1 for human-driven clients or an oak_agent_ bearer token for autonomous agents. The server includes standard tools like list_my_tools, check_permission, list_pending_approvals, and check_approval_status. For organizations using the OakGuard gateway, the server can also act as a secure transport that forwards approved calls to registered MCP servers. Every decision, whether allowed, requires_approval, or disabled, returns a signed decision receipt to ensure the integrity of the governance process.
What you can do with it
- 1Request human oversight for risky actionsAn agent can submit a tool call with a reason to trigger a manual approval workflow.
- 2Verify tool execution permissionsA developer can have an agent check if a specific tool call is permitted or blocked by policy before attempting it.
- 3Monitor pending approval requestsAn agent can poll the status of a request using a reference number to see if a human has granted permission.
Written from the project's README. Every use case is checked against a quote from it.
How to install Oakallow MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Oakallow MCP in Claude Code
$ claude mcp add --transport http oakallow-mcp https://api.oakallow.io/mcpInstall Oakallow MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"oakallow-mcp": {
"url": "https://api.oakallow.io/mcp"
}
}
}Install Oakallow MCP in VS Code
.vscode/mcp.json
{
"servers": {
"oakallow-mcp": {
"type": "http",
"url": "https://api.oakallow.io/mcp"
}
}
}Install Oakallow MCP in VS Code CLI
$ code --add-mcp '{"name":"oakallow-mcp","type":"http","url":"https://api.oakallow.io/mcp"}'Install Oakallow MCP in Codex
$ codex mcp add oakallow-mcp --url https://api.oakallow.io/mcpInstall Oakallow MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.oakallow-mcp] url = "https://api.oakallow.io/mcp"
Install Oakallow MCP in Gemini CLI
$ gemini mcp add -s user --transport http oakallow-mcp https://api.oakallow.io/mcpInstall Oakallow MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"oakallow-mcp": {
"url": "https://api.oakallow.io/mcp",
"type": "http"
}
}
}Oakallow MCP tools 6
Detected from the READMElist_my_toolscheck_permissionlist_pending_approvalscheck_approval_statusreasonagent
| list_my_tools | — | |
| check_permission | — | |
| list_pending_approvals | — | |
| check_approval_status | — | |
| reason | — | |
| agent | — |
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableoakallow/oakallow-mcp is public and reachablegithub.com/oakallow/oakallow-mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-23github.com/oakallow/oakallow-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model6 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubOakallow 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
Oakallow injects a governance checkpoint into a workflow that may also use other connectors. An agent does its investigative work (for example, looking up an account through another connector), forms a recommendation, and calls Oakallow to request approval for the action. A human approver then decides in the Oakallow dashboard or mobile app, under enforced multi-factor authentication.
The connector is a requester and pass-through, not a decider:
- It can list your tools, check permissions, request approvals, return a signed receipt for every decision, and, for servers connected through the OakGuard gateway, forward a call once it is approved.
- It cannot approve or deny on a human's behalf. Decisions happen on a separate, MFA-bound surface (the dashboard), never over the connector.
Standard tools
| Tool | Purpose | Reads only |
|---|---|---|
list_my_tools |
Enumerate the tools available to the signed-in user in the named org (org arg; see below) |
yes |
check_permission |
Ask whether a given tool call would be allowed, require approval, or be blocked (takes an org arg; see below) |
yes* |
list_pending_approvals |
List approval requests still awaiting a human decision | yes |
check_approval_status |
Poll a pending approval request by reference number | yes |
* check_permission returns a read-only verdict only. It does NOT create an approval or
a reference. (The approval and its REF-… are created when you call the gated tool itself
through oakallow.) It does have one side effect by design: checking an unregistered tool
makes Oakallow auto-create a gated draft entry for it (with conservative, fail-closed
defaults) so the eventual call is governed and the owner can triage it from the dashboard.
This is intentional: an unknown tool is never silently trusted.
Choosing an organization
An Oakallow account can have more than one organization, and each org sets its own tools, permission rules, approvers, and alert paths. So an action must be checked against the right org, because that is what determines who gets asked to approve and under which rules.
check_permission and list_my_tools accept an optional org argument: the org's
external id (e.g. org_oak_…). The rule:
- One org on your account: omit
org. The connector uses your only org. - More than one org: pass
orgnaming the org the action targets. If you omit it, the call is refused with guidance rather than guessing the wrong org.
You don't ask the connector to list your orgs; there is no org-enumeration tool. Instead,
download the org-specific skill from that org's dashboard. Each org's skill carries its
own org id and tells the agent to pass it. Install one skill per org you operate in; the
agent reads the matching skill and passes the right org on every call.
The connector authorizes the org you pass against your signed-in identity: you can only
target an org you can actually act in (you are its team owner/admin, or you are in that
org's approver group). Passing an org you don't have access to is refused. The skill is a
convenience, not a grant of access.
Calling a governed tool
Alongside the four standard tools, tools/list returns the customer-defined tools your
org has approved. Calling one of those through oakallow is how an approval gets created:
there is no separate "request approval" tool. A direct tool accepts two optional
arguments, plus org as above:
| Argument | Purpose |
|---|---|
reason |
Short, non-sensitive summary of why the call is being made. This is what the human approver reads. Oakallow redacts SSN, card, email, phone, and address patterns before storing it. |
agent |
An identifier for the calling agent (a name, code, or number). The org's governance report uses it to show which agent submitted each call instead of attributing everything to the signed-in account. Send the same value consistently. Ignored when the caller authenticates with an oak_agent_ token, whose own identity is used. |
The response is one of allowed (run the action on its own connector), requires_approval
(an approval request was created and a REF-… is returned for polling with
check_approval_status), or disabled (stop; the action is blocked by policy).
Signed decision receipts
Every permission decision on an approved tool returns a signed decision receipt,
whatever the verdict: allowed, requires_approval, and disabled are all signed the
same way. The receipt is an HMAC-SHA256 signature over the decision, the tool, a hash of
the call's parameters, the tenant, resource, method, and org, and it is stored so the
decision can be re-verified later. A disabled receipt is the proof that oakallow blocked
the action.
If a decision cannot be signed or recorded, the check fails closed: oakallow returns no verdict rather than one it cannot prove.
OakGuard gateway
By default oakallow is a checkpoint beside your tools: it decides, and you execute. OakGuard lets an org register its own MCP servers with oakallow so that oakallow becomes the transport to them instead:
- OAuth 2.1 is mandatory downstream. Registration is refused unless the server advertises the OAuth 2.1 essentials (authorization code with S256 PKCE, RFC 9728 and RFC 8414 discovery, no password grant). oakallow registers itself as the server's OAuth client and keeps the downstream tokens encrypted.
- Tools appear under their real names and schemas in
tools/list. Newly discovered tools land as drafts that require approval until an admin enables them. - A call is forwarded only after it is allowed by the permission rules or approved by a human. Each approval rides downstream exactly once.
- Payloads pass through but are not kept. oakallow carries the request and response over TLS on both legs and does not store or log them. Receipts and the audit log record the decision, not the data.
Servers are registered, paused, and revoked from the OakGuard tab in the dashboard.
Resources
oakallow exposes two read-only MCP resources. They are preflight signals an agent (or a
client UI) can read before committing to route an action through oakallow. Both require
the mcp:read scope, neither is a tool call, and neither is billed.
| Resource | Returns | Reads only |
|---|---|---|
oakallow://status |
Liveness of the connector for the signed-in session: status, endpoint, server version, protocol version, and the granted scopes. A successful read is itself the proof the session is valid. No account identity or PII is returned. | yes |
oakallow://credits |
Whether a governed call would currently be funded for the org this session resolves to, so an agent can fail fast before requesting an approval that could not be paid for. | yes |
oakallow://credits is scoped to the caller's own billing org and resolves it the same
way a real tool call does, so a can_fund: true result genuinely means the eventual
approval will be funded (including team-pool fallback). It returns only a can_fund
boolean and the org's name and external id. It deliberately discloses no balance figures:
dollar amounts are surfaced only to the team owner in the dashboard, never over the
connector. If the session resolves to no org, or to more than one, it returns
can_fund: false with a reason rather than guessing which org would be billed.
Connecting
There is no anonymous access. An oakallow account is the prerequisite for connecting,
and the endpoint accepts two credential types: interactive OAuth 2.1 (PKCE) for a
human-driven client, or an oak_agent_ bearer token for an autonomous agent (see
Autonomous agents below).
For the human-driven OAuth path, add https://api.oakallow.io/mcp as a custom connector
in your MCP client (Claude, Claude Desktop, Cowork, ChatGPT, or any Streamable HTTP MCP
host). You will be redirected to sign in to Oakallow and approve the requested scopes:
mcp:read: list tools, view pending approvals, check permissions, read activity.mcp:write: create approval requests and mint run tokens.
You don't configure any of this by hand: an unauthenticated request returns 401 with a
WWW-Authenticate header pointing to the endpoint's RFC 9728 protected-resource metadata
(/.well-known/oauth-protected-resource), so a spec-compliant MCP client discovers the
authorization server and runs the OAuth flow automatically.
See examples/ for a Claude Desktop config, an OAuth flow walkthrough, and an
oak_agent_ token walkthrough. tools.json has the exact schemas of the
standard tools.
Autonomous agents (oak_agent_ token)
OAuth assumes a human can complete the interactive sign-in. An autonomous agent that runs
on its own authenticates to the same https://api.oakallow.io/mcp endpoint with a
pre-issued bearer token instead: Authorization: Bearer oak_agent_.... The endpoint
checks for an oak_agent_ bearer before the OAuth provider, so no consent screen or
interactive login is involved.
An agent identity is scoped to one organization, can submit and check permission requests but never approve, is rate-limited per identity, and is stored only as a SHA-256 hash (the raw token is shown once at creation). Provision one from the dashboard's Account → Agents page (owner/admin only). See oakallow.io/info/agents for the full model.
Skill
SKILL.md is an agent skill that documents when and how to use the
oakallow tools: the request, approve, poll, and act workflow, how to phrase
approval reasons, and what to do on allowed, requires_approval, or disabled
verdicts. Point your agent at it to govern tool actions correctly.
Trigger prompts
PROMPT.md has short, copy-paste one-liners to drop into your
agent's system prompt so it actually consults the skill. The skill is the
procedure; a trigger prompt is what makes the agent look. Three options, from
"gate every tool call" to "gate a customer-named set," plus an inline example
pattern for a real request.
How a governed call works
- The agent calls the tool through Oakallow with its credential, a
reason, and itsagentid. - Oakallow resolves the permission rule for the specific tool, tenant, and resource, and signs a decision receipt for the verdict.
- If the action is allowed, the agent performs it: on its own connector for a direct tool, or Oakallow forwards it for an OakGuard gateway tool.
- If approval is required, an approval request is created, a human is notified, and the
agent receives a
REF-…to poll. Once a human approves under MFA, the action runs exactly once. - Oakallow writes an immutable audit row capturing the outcome.
For direct tools, Oakallow lives outside the execution path: it governs and records what was reported, and it does not run your tools or receive your tool parameters beyond a PII-scrubbed reason. For OakGuard gateway tools, it is the transport for approved calls but still keeps none of the payloads.
Outside MCP, the REST API (POST /v1/tokens/mint) can also mint a single-use,
HMAC-signed run token that binds the tool and its parameters, for your backend to verify
before executing.
License
See LICENSE.
Changelog
See CHANGELOG.md.
© Islemonics Studios LLC. Patent pending.
Oakallow MCP questions
How do I add Oakallow MCP to Claude Code?
Run claude mcp add --transport http oakallow-mcp https://api.oakallow.io/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Oakallow MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Oakallow MCP provide?
It exposes 6 tools, including list_my_tools, check_permission, list_pending_approvals, check_approval_status, reason.
How does Oakallow handle human approvals?
A human approver decides on requests via the Oakallow dashboard or mobile app under enforced multi-factor authentication.
Can the connector approve or deny actions on behalf of a human?
No, the connector is a requester and pass-through; all decisions must happen on a separate, MFA-bound surface.
What happens if an unknown tool is checked?
Oakallow will automatically create a gated draft entry for the unknown tool with conservative, fail-closed defaults to ensure it is governed.
Does Oakallow store the data sent during tool calls?
For OakGuard gateway tools, payloads pass through but are not kept; the audit log records the decision, not the data.