How We Built Harvey’s Connector Library

Harvey Blog ·

A technical overview by the author of Harvey’s Connector Library architecture, its security review process for connectors, MCP connector approval requirements, and the adapter layer’s design for handling vendor-specific implementation differences. Lies 4 Standpunkte mit Belegen und Links zu den Originalquellen.

Auf einen Blick

  • Connector Library enforces permissions and handles provider differences

    Building the Connector Library involved making external tools available to AI agents while enforcing user permissions and accommodating technical differences across service providers.

    Unterstützendes Moment lesen · Absatz 1
  • Security review precedes launch and covers core threat scenarios

    Before a connector launches, Harvey's security team reviews it against threat scenarios including prompt injection, misuse of write capabilities, credential compromise, cross-tenant leakage, and supply-chain risk; at runtime, each tool call must still pass permission and policy checks.

    Unterstützendes Moment lesen · Absatz 12
  • MCP connectors require vendor-submitted tool specs and per-tool security review

    For MCP connectors—where the vendor operates the server—Harvey requires the vendor to submit its full tool list, capability scope, hosting and auth details, data-processing regions, and test credentials; the security team then reviews each tool individually, approves or rejects it, assigns a risk level, and records decisions in a code-shipped registry.

    Unterstützendes Moment lesen · Absatz 14
  • Adapter follows server authorization behavior

    For authorization, Harvey’s adapter layer follows the behavior a server exposes: it can discover metadata directly when no challenge is sent, accept valid tokens returned with either 200 or 201, and request the scopes the server advertises.

    Unterstützendes Moment lesen · Absatz 26

Wichtige Passagen4

Zugeordnete Passagen mit dem Kontext zur Überprüfung. Öffnen Sie den Originaltext, um die Quelle zu prüfen.

MCP connector approval

MCP connectors require vendor-submitted tool specs and per-tool security review

Originalauszug

An MCP member's server is operated by the vendor, so the review has to judge a system someone else runs, and it gets an extra layer of admission. The vendor submits its full tool list and capability scope, hosting and auth details, data-processing regions, and test credentials, and the security team reviews the tools one by one, deciding for each whether it is approved and assigning its risk level.
Kontext

A native member is a wrapper we wrote around the vendor's API, and it goes through the same security review: which of the vendor's APIs we call and which scopes we request are what the security team signs off on. This way, approval is a hard gate before engineering integration begins. Those decisions land in a registry that ships with the code: a structured URL matcher, the vendor's full advertised tool list, the subset that may be invoked, and a hand-written risk and capability annotation for each.

security review process

Security review precedes launch and covers core threat scenarios

Originalauszug

Connector security starts before a tool reaches users and continues when the agent calls it. Before launch, our security team reviews threats such as prompt injection, misuse of write capabilities, credential compromise, cross-tenant leakage, and supply-chain risk. At runtime, each call must still pass the applicable permission and policy checks.
adapter layer design

Adapter follows server authorization behavior

Originalauszug

We handle these differences in an adapter layer. For authorization, we follow the behavior a server actually exposes: we can discover metadata directly when it does not send a challenge, accept valid tokens returned with either 200 or 201, and request the scopes it advertises.

Quelle & Methodik

Diese Standpunkte sind mit ihren Originalquellen verknüpft. Paraphrasen sind gekennzeichnet und keine wörtlichen Zitate.

Transkript oder Quellenmaterial öffnen (wird in einem neuen Tab geöffnet)Ein Problem melden