# Shared services · Neural Inverse Govern > The services under Neural Inverse Build and Govern alike: a vault, per-organisation keys, DLP, gateways for MCP tools and remote agents, sandboxes, data residency, the console assistant and harness packs. Source: https://neuralinverse.com/govern/shared-services/ --- ![](/photos/hangar.jpg) [Neural Inverse Govern / Shared services](https://neuralinverse.com/govern/) # Secrets, keys, sandboxes and assistants, held to the same rules as everything else. The services under Neural Inverse Build and Govern alike: a vault, per-organisation keys, DLP, gateways for MCP tools and remote agents, sandboxes, data residency, the console assistant and harness packs. Vault Write-only secrets, dynamic credentials Keys Per organisation, versioned and rotated Sandboxes Isolated Firecracker runtimes Assistant Off by default, acts as the person Harness packs Signed and gated on evals Overview Shared services are the parts of the platform both products rely on. Secrets live in one vault and are never returned in plain form, data is encrypted under each organisation's own keys, one DLP engine applies across models, tools, agents and context, and sandboxes, the console assistant and harness packs are governed by the same identity, policy and audit as everything else. [What it does ↓](https://neuralinverse.com/#capabilities)[How it works ↓](https://neuralinverse.com/#workflow)[Enforced and recorded ↓](https://neuralinverse.com/#enforcement)[Where it runs ↓](https://neuralinverse.com/#where)[Get started ↓](https://neuralinverse.com/#get-started) What it does ## What the shared services provide. Only the services that are working today. - **Vault secrets:** Versioned key-value secrets, shared per mount at use, read and write levels. Every vault request is written to the audit log. - **Dynamic credentials:** Short-lived credentials for databases, AWS, Azure and Google Cloud, a PKI and SSH certificate authority, and transit encryption, with leases you can renew and revoke. - **Machine logins:** Workloads sign in to the vault with AppRole, client certificates, JWT, Kubernetes service accounts or a Govern agent's identity, instead of a stored token. - **AI keys behind placeholders:** Agents use AI provider credentials through placeholders that are replaced on the way out, so the real key never reaches the agent. - **Secrets into sandboxes:** Secrets pushed into a sandbox or workspace land only in memory-backed storage, and only for people who may use both the secret and the target. - **Encryption keys:** Per-organisation keys, versioned and rotated, sealed by a deployment master key kept outside the database. Data is encrypted with AES-256-GCM under per-object data keys. - **One DLP engine:** Built-in and custom patterns, applied on model prompts and answers, MCP tool calls, agent-to-agent traffic, context sources and app activity, with the action set by the data's classification. - **MCP gateway:** A reviewed catalog of MCP servers and tools, assigned to the organisation, teams or projects. The gateway applies assignment, DLP and rate limits, holds calls that need approval and logs every decision. - **Agent gateway:** Remote agents reached over the Agent2Agent protocol, with deny-by-default allow rules, credentials held in the vault, a classification ceiling, a delegation depth limit and DLP in both directions. - **Sandboxes:** Isolated runtimes for agent and user work, started from templates within your organisation's limits and each member's quota, with exec, files, logs and an MCP endpoint agents can drive. - **Approved artifacts:** What a sandbox run produces is encrypted at rest and approved or rejected before it is applied. An administrator can stop every sandbox of the organisation at once. - **Data residency:** Govern runs where you deploy it. Models can be pinned to regions and limited by classification, a project's residency rule refuses models outside it, and every audit entry records the region that wrote it. - **Console assistant:** Answers questions about your organisation in the console, with no identity of its own: every tool call runs as the signed-in person, models are reached only through the AI Gateway, and every answer cites its records. - **Assistant proposals:** The assistant drafts a fixed set of changes, such as creating a project or binding a role. Each runs only when the same person confirms the exact request within five minutes, once, through the target's own checks. - **Harness packs:** Signed developer-experience packs for the Editor's agent engines: instructions, skills, tools, MCP servers and evals, assigned to the organisation, teams or projects. Packs are not policy and cannot weaken it. - **Experiments and rollout:** A/B experiments between pack versions with staged rollout, gated on passing evals, with outcome metrics made of identifiers and counts only, never code or prompts. How it works ## How a change drafted by the console assistant runs. The assistant can propose a change. Only the person can make it. 1. Ask A person asks in the console; the assistant reads records through Govern's API as that person. 2. Draft It drafts one of a fixed set of changes, stored as the exact request. 3. Pre-check The request is checked as the person; a failed check disables the card. 4. Confirm The same person confirms it in the same session within five minutes. 5. Run It runs once, through the target route's own checks, MFA and two-person rules included. 6. Record The audit entry carries the proposal id, so auditors can tell it from a typed change. Who uses it ## Built for every role that answers for AI. - **Platform engineers:** Run the vault and sandboxes, and publish and assign harness packs. - **Security teams:** Manage keys and DLP patterns, review MCP servers and set allow rules for remote agents. - **Developer experience leads:** Run experiments between harness pack versions and promote the one that performs. - **Administrators:** Turn on the console assistant, choose its models and set how long transcripts are kept. Enforced and recorded ## Held to the same rules as everything else. Each service enforces its own boundary on the server and writes to the same audit log. Enforced - **Secrets:** AI provider keys and other credentials are write-only: responses show only a hint, a version and the rotation time. - **MCP and agent calls:** Decided in the gateways for every call: assignment or allow rules, DLP, rate limits and approvals. - **Assistant:** Can never see or do more than the person using it. Deletes, credentials, billing and anything that sends data to an address are never proposed. - **Harness packs:** The Editor refuses unsigned or tampered packs, and agent policy always wins over anything in a pack. Recorded - **Vault and gateways:** Every vault request, and every MCP gateway decision with its latency, DLP findings and approval. - **Assistant turns:** One audit event per turn with a keyed hash of the prompt, never the prompt itself. Transcripts are encrypted under the organisation's key for the retention you set. - **Pack changes:** Pack, version, assignment, experiment and eval changes, inside the transaction of the change. The server can use Go's FIPS 140-3 cryptographic module and refuse to start without it. Whether this meets a validation requirement is for you and your assessor to decide. Where it runs ## On your infrastructure, with your keys. [Deployment options](https://neuralinverse.com/deployment/) - **Master key:** The deployment master key that seals every organisation's keys is kept outside the database by your operator. - **Sandboxes:** Run on compute you operate, as part of your own installation. - **Air-gapped:** The console assistant uses local models served by your gateway only; if no model passes its conformance check, it stays off. - **Hosted by us:** We run it for you. Custom harness packs and experiments depend on the plan; a self-hosted installation includes everything. Get started ## Set it up with the documentation. - [Security architecture](https://neuralinverse.com/docs/security/) - [Console assistant](https://neuralinverse.com/docs/govern/console-assistant/) - [Harness packs](https://neuralinverse.com/docs/govern/harness-packs/) - [Guardrails and DLP](https://neuralinverse.com/docs/govern/guardrails/) - [Deploy and operate](https://neuralinverse.com/docs/deploy/) Related [AI Gateway → Approved models, DLP, guardrails, budgets and rate limits for every model request.](https://neuralinverse.com/govern/ai-gateway/)[Agent policy and approvals → Allow, ask and deny rules for coding agents, with named approvers.](https://neuralinverse.com/govern/agent-policy/)[Audit and evidence → A hash-chained audit log you can verify offline, and evidence toward your frameworks.](https://neuralinverse.com/govern/audit/) ![](/photos/team.jpg) ## Talk to our team. Neural Inverse is available by request. We work with your engineering, security and procurement teams from the first conversation. [Request access](https://neuralinverse.com/contact/?topic=access)[Contact us](https://neuralinverse.com/contact/)