Node8
Contact

AI Connectors · Developer Tools

Kastra

Read-only view of AI agent authorization decisions and audit trails

Listed in Claude · 13 published tools · Community-listed

Claude connector docs kastra.ai

Overview

What Kastra does

Kastra evaluates agent actions against written policy and keeps a tamper-evident record of what was allowed, denied, or held. The connector is deliberately one-directional. After OAuth consent and the selection of a single environment, it can read decisions and their outcomes, policies and per-rule statistics, incidents and pending approval checkpoints, audit-chain verification results, activity trends, and masked API key metadata.

What it cannot do is written into the listing: no writes, no settings changes, no reach into another tenant, and no exposure of raw prompt content or plaintext keys. Thirteen tools are published, access stays scoped to the selected environment, and it can be revoked from connector settings.

Who it is for

Security and compliance owners accountable for how autonomous agents behave.

Tool surface

Nothing can be enumerated from outside, since the server requires the OAuth grant before it responds, so the read-only characterisation of its thirteen tools rests on the publisher's description.

Availability

Where Kastra is listed

Kastra is listed in the Claude connectors directory only. Kastra Labs has no app under the same domain in the ChatGPT directory; 392 of the 3,150 products here are on both marketplaces, and this is not one of them.

The MCP server behind a Claude connector is usually the same server a ChatGPT app would need, so the absence is a distribution decision rather than a technical one.

Claude listing

In the Claude connectors directory

Kastra publishes 13 tools to Claude. That is a mid-sized surface: 54.3% of the 1,253 Claude-listed connectors expose fewer.

That is exactly the median for Claude-listed connectors under Developer Tools, where 95 publish counts and 13 is the middle of the distribution.

It falls in the 11-20 tools band, which holds 22.5% of the Claude directory.

Kastra publishes a remote MCP endpoint. Claude connects to it over HTTP; there is nothing to install locally.

Every connector in the Claude directory is remote, all 1,253 of them, so transport is not a differentiator there.

Publisher
Kastra Labs
Verification
Community-listed (61.5% of the Claude directory)
Filed under
Developer Tools
Endpoint
https://api.kastra.ai/mcp/account
Published tools
13 · 11-20 tools band
Depth rank in Developer Tools
48 of 95
Snapshot
August 2026

Kastra is community-listed in the Claude directory, the tier 770 of 1,253 connectors sit in (61.5%). It is the default for a self-published server, and says nothing either way about quality.

In the publisher's words

How Kastra Labs describes it

Kastra is an AI authorization platform that evaluates your AI agents’ actions against your policies and maintains a tamper-evident audit trail. This connector gives Claude read-only access to your Kastra account, allowing you to ask questions about your governance posture in plain language instead of navigating the console. After you authorize the connector through a Kastra OAuth consent screen and select an environment, Claude can read—but never modify—the following: •⁠ ⁠Decisions and their outcomes (allow, deny, and hold) •⁠ ⁠Policies, environments, and per-rule statistics •⁠ ⁠Incidents and HOLD approval checkpoints •⁠ ⁠Audit-chain verification results and governance audit logs •⁠ ⁠Activity statistics and trends •⁠ ⁠Onboarding governance preferences and masked API key metadata Access is limited to your tenant and the specific environment you select during authorization. The connector cannot write data, modify settings, access other tenants, or expose raw prompt content or plaintext API keys. You can revoke access at any time through your connector settings.

Quoted from the connector's own Claude directory listing as captured in August 2026. Node8 did not write it and does not vouch for it.

Nearby

Other Developer Tools connectors

Apiiro Guardian

Application security risk context from an Apiiro deployment

Claude

Affirmed AI

Vulnerability findings and endpoint inventory from Affirmed

Claude

Armature

Inspect MCP server activity and agent sessions

ChatGPT

CodeRabbit

CodeRabbit review workflows applied to current working changes

ChatGPT

All 188 Developer Tools connectors

This is an independent catalogue entry compiled by Node8 from Kastra's public marketplace listing as it stood in August 2026. Listing facts come from the marketplaces; the comparisons against the rest of the directory and any live-endpoint measurements are Node8's. Node8 is not affiliated with Kastra Labs, and inclusion here is not an endorsement.

Want your company reachable inside ChatGPT and Claude?

Node8 builds MCP servers end to end: deciding which tools are worth exposing, the authentication and permission model, the review submissions, and the onboarding that gets them used. One server serves ChatGPT, Claude, and Microsoft Copilot.

See how it works