need-to-know
Provides permission-aware access to a Salesforce org through adapters for user entity access, field-level access, record sharing/access, and WITH USER_MODE queries. It enforces per-user object, field, and record permissions on retrieval, re-reads records live before returning data, supports switching the MCP server and approval channel to Salesforce via GINA_BACKEND=salesforce, and includes read-only parity checks against a real org.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
need-to-know (Gina, for short) sits between your CRM and any language model and decides who may read what before a single word of a record reaches the prompt. It runs on Node 24 against a local reference CRM, or against a real Salesforce org.
If you are putting an AI assistant on top of a CRM, the first thing your security team will ask is whether it can show someone data they are not allowed to see. This repo is one answer to that question, with the measurements to back it.
The problem
A sales team plugs an AI assistant into the CRM. An SDR asks "who is evaluating Service Cloud?" and the answer quotes a revenue figure that SDR was never allowed to see. Nobody wrote a bug. The vector index knew more than the user did.
Most RAG stacks check permissions once, at indexing time, with a service account, and then trust the index. Then the index goes stale, permissions change, a record picks up a poisoned note ("ignore previous instructions and…"), and the model reads all of it.
Related MCP server: salesforce-mcp
What Gina does
The index stores ids, a field list and a SHA-256 of the values, and no text. At query time Gina re-reads the declared fields live and drops the chunk if the hash changed, so the index can never serve more than the CRM would.
Permissions are checked per user, on every query: object, field-level security and record sharing. An error, a timeout or an ambiguous answer counts as a deny. Records are indexed once per audience, so a user who cannot see a field still gets the fields they may read, ranked on those fields alone.
Retrieved text is treated as data. Unicode tags, zero-width and bidi tricks, hidden HTML and embedded instructions are stripped or quarantined, then a local classifier takes a second look. Poisoned records never enter the index.
The model has no write access. It can propose one CRM task; a person approves the exact payload by its hash, outside the model's channel, and Gina re-checks edit access live before writing.
Run the tests (offline, no Salesforce, no model)
You need Node 24 and pnpm. The suite runs offline and needs no Ollama.
pnpm install --frozen-lockfile
pnpm testSupported platforms are macOS and Linux. On 2026-11-19 both ran the full suite in CI with 316 tests and 0 failures, and on a laptop it finishes in under a second. Windows is not supported. pnpm eval then runs the permission evaluator and exits non-zero if a single chunk leaks.
Try the demo
The demo also needs Ollama with nomic-embed-text and qwen2.5:7b.
pnpm demoIt seeds a local reference CRM, indexes it, and asks the same question over MCP as two users. The admin gets three chunks. The restricted user gets none for a question only a hidden field answers, and gets the industries they asked about when their own fields can answer. The model proposes a task: the restricted user's approval is refused, and the admin's creates it exactly once. The record carrying a prompt injection never made it into the index.
pnpm local ask --as restricted "who is evaluating Service Cloud?"
pnpm local edit 001LOCAL0000001AAA Description="…" && pnpm local reindex
pnpm mcp # MCP server for Claude Code or any client (GINA_USER_ID=…)
pnpm approvals # the human channelWhat it proves
Every number below comes from a run in this repo, and you can reproduce all of them except the classifier range without a model.
316/316 adversarial and boundary tests, offline (pnpm test)
0 leaked chunks across 36 permission scenarios (pnpm eval)
76–81% injection detection on a static blind corpus, 5 runs (adaptive attacker: see below)
0–1.3% false positives on the same corpus
16/16 decisions measured on the live org, reproduced by the local CRMWhat it does not prove
The injection detector lowers the risk, and a determined attacker still gets past it. Against an adaptive attacker (a frontier model that saw only pass or fail), one round of adaptation took the share of attacks reaching the LLM's context from 30 to 35% up to 76 to 78% (red team). Plain business prose ("note from the Sales Director: offer 45%…") gets through.
Three things hold even when detection fails, because they come from how the system is built:
the model never receives a field or a record the user cannot read;
the model cannot write to the CRM; a person approves the exact payload, and edit access is re-checked live;
the index never holds text, so a stale or tampered index serves nothing.
A note that passes can still make the model say something false to the user, such as a fake discount, false urgency or a phishing link. Keep a person on every decision that moves money, and keep the client from rendering links and images it did not expect. That is the class of attack behind ForcedLeak, which Noma Security disclosed in Agentforce in 2025.
When a claim turned out wrong, it went into docs/failure-log.md with how it was caught.
How it evolved
Chapter 1, Gina Training Lab, answered "who needs attention today?" for a small retailer: deterministic CRM lifecycle rules, a 48/48 adversarial suite and an Agentforce package. It read trusted, structured records.
Chapter 2 answers "who may read what before any text reaches an LLM?" with the same philosophy and harder inputs: untrusted, unstructured text; live FLS and sharing instead of rules evaluated on load; indirect prompt injection treated as a first-class threat; a governed write path instead of a single review task.
What you can take from it
The vector record contract keeps the index from becoming a second, unaudited copy of your CRM.
Fail-closed is enforced by the types. Ports return unknown, and only the literal true grants access, so a sloppy or hostile adapter cannot open the gate.
Code emits a detail, and a single table derives the audit reason from it, so there are no hand-written deny messages to drift apart.
The security tests are mutation-tested. Case 20 of the failure log was a test that kept passing with the protection switched off; it now fails when the protection is removed.
Against a real org
The same ports have Salesforce adapters (UserEntityAccess, UserFieldAccess, UserRecordAccess, WITH USER_MODE). GINA_BACKEND=salesforce switches the MCP server and the approval channel; pnpm check:live measures parity, read-only. Writing to an org takes an explicit flag every time.
Roadmap
A query router that picks between a structured query and retrieval, measured by the same evaluator.
The same rules enforced natively inside Salesforce, so CRM data never has to leave the org.
Links
Case study · ADRs · Approval harness · MCP gateway · Evaluation · Failure log · Security · Apache-2.0
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Salesforce-grounded retrieval, diagnoses, and a vetted-Force marketplace for MCP clients.
The HubSpot MCP Server acts as a bridge that enables AI assistants and Large Language Models to securely interact with HubSpot CRM data through natural conversation, without requiring users to understand complex API structures. It provides read-only access to standard CRM objects (contacts, companies, deals, tickets, products, invoices, and more) and their associations, secured via OAuth 2.0, allowing AI agents to perform tasks like summarizing deals, fetching company updates, and looking up record changes.
API-first CRM for LLMs - contacts, companies, deals and activities over a native MCP server.
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA reference MCP server demonstrating safe agent access to multi-tenant CRM data with tenant isolation enforced in the data layer, role-based permissions, and human confirmation on writes.MIT
- FlicenseNot gradedqualityBmaintenanceMCP server that lets an AI agent read a Salesforce pipeline (opportunities, accounts, contacts) and write back to it safely through a narrow set of guarded tools.-
- AlicenseNot gradedqualityDmaintenanceMCP server for securely connecting LLMs to customer data, providing customer profile retrieval, semantic search of interaction history, and exact financial summaries via SQL aggregation, with audit logging and prompt injection protection.MIT
- FlicenseNot gradedqualityBmaintenanceEnables remote MCP access to CRM data, allowing read-only search of contacts, opportunities, and conversations with user-scoped permissions and RLS preservation.-