Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
Fail-closed privacy layer that pseudonymises enterprise API data for LLM agents and MCP clients.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
LOADER_PATH, DATAPRISM_SECURITY_JWT_ISSUER, DATAPRISM_SECURITY_JWT_AUDIENCE, DATAPRISM_SECURITY_JWT_JWK_SET_URI, DATAPRISM_SECURITY_JWT_ISSUER_DISCOVERY_URI, DATAPRISM_SECURITY_CALLER_CLAIMS_PRINCIPAL, DATAPRISM_SECURITY_CALLER_CLAIMS_ROLES, DATAPRISM_SECURITY_CALLER_CLAIMS_INVESTIGATION, DATAPRISM_SECURITY_POLICY_PURPOSES, DATAPRISM_SECURITYPOLICY_ROLES_INVESTIGATOR, DATAPRISM_PRIVACY_PROFILE, DATAPRISM_PRIVACY_SCOPE_LIFETIME, DATAPRISM_PRIVACY_HMAC_KEY_KEY_ID, DATAPRISM_PRIVACY_HMAC_KEY_ENVIRONMENT_VARIABLE, DATAPRISM_PRIVACY_HMAC_KEY_PROVIDER_REFERENCE, DATAPRISM_AUDIT_SINK, DATAPRISM_AUDIT_WRITER_ID, DATAPRISM_AUDIT_FILE_PATH, DATAPRISM_METRICS_SINK, DATAPRISM_HAZELCAST_TOPOLOGY, DATAPRISM_HAZELCAST_CLUSTERNAME, DATAPRISM_HAZELCAST_JOIN_MODE, DATAPRISM_HAZELCAST_JOIN_MEMBERS, DATAPRISM_HAZELCAST_MEMBER_PORT, DATAPRISM_OPERATOR_ENABLED, DATAPRISM_OPERATOR_PORT, DATAPRISM_OPERATOR_REQUIREDAUDIENCE, DATAPRISM_OPERATOR_REQUIREDSCOPE, DATAPRISM_SOURCES_CUSTOMER_BASE_URL, DATAPRISM_SOURCES_CUSTOMER_TIMEOUTYou need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"data-prism": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"LOADER_PATH",
"-e",
"DATAPRISM_SECURITY_JWT_ISSUER",
"-e",
"DATAPRISM_SECURITY_JWT_AUDIENCE",
"-e",
"DATAPRISM_SECURITY_JWT_JWK_SET_URI",
"-e",
"DATAPRISM_SECURITY_JWT_ISSUER_DISCOVERY_URI",
"-e",
"DATAPRISM_SECURITY_CALLER_CLAIMS_PRINCIPAL",
"-e",
"DATAPRISM_SECURITY_CALLER_CLAIMS_ROLES",
"-e",
"DATAPRISM_SECURITY_CALLER_CLAIMS_INVESTIGATION",
"-e",
"DATAPRISM_SECURITY_POLICY_PURPOSES",
"-e",
"DATAPRISM_SECURITYPOLICY_ROLES_INVESTIGATOR",
"-e",
"DATAPRISM_PRIVACY_PROFILE",
"-e",
"DATAPRISM_PRIVACY_SCOPE_LIFETIME",
"-e",
"DATAPRISM_PRIVACY_HMAC_KEY_KEY_ID",
"-e",
"DATAPRISM_PRIVACY_HMAC_KEY_ENVIRONMENT_VARIABLE",
"-e",
"DATAPRISM_PRIVACY_HMAC_KEY_PROVIDER_REFERENCE",
"-e",
"DATAPRISM_AUDIT_SINK",
"-e",
"DATAPRISM_AUDIT_WRITER_ID",
"-e",
"DATAPRISM_AUDIT_FILE_PATH",
"-e",
"DATAPRISM_METRICS_SINK",
"-e",
"DATAPRISM_HAZELCAST_TOPOLOGY",
"-e",
"DATAPRISM_HAZELCAST_CLUSTERNAME",
"-e",
"DATAPRISM_HAZELCAST_JOIN_MODE",
"-e",
"DATAPRISM_HAZELCAST_JOIN_MEMBERS",
"-e",
"DATAPRISM_HAZELCAST_MEMBER_PORT",
"-e",
"DATAPRISM_OPERATOR_ENABLED",
"-e",
"DATAPRISM_OPERATOR_PORT",
"-e",
"DATAPRISM_OPERATOR_REQUIREDAUDIENCE",
"-e",
"DATAPRISM_OPERATOR_REQUIREDSCOPE",
"-e",
"DATAPRISM_SOURCES_CUSTOMER_BASE_URL",
"-e",
"DATAPRISM_SOURCES_CUSTOMER_TIMEOUT",
"ghcr.io/aindriub/data-prism-server:0.7.1"
],
"env": {
"LOADER_PATH": "your-value",
"DATAPRISM_SECURITY_JWT_ISSUER": "your-value",
"DATAPRISM_SECURITY_JWT_AUDIENCE": "your-value",
"DATAPRISM_SECURITY_JWT_JWK_SET_URI": "your-value",
"DATAPRISM_SECURITY_JWT_ISSUER_DISCOVERY_URI": "your-value",
"DATAPRISM_SECURITY_CALLER_CLAIMS_PRINCIPAL": "your-value",
"DATAPRISM_SECURITY_CALLER_CLAIMS_ROLES": "your-value",
"DATAPRISM_SECURITY_CALLER_CLAIMS_INVESTIGATION": "your-value",
"DATAPRISM_SECURITY_POLICY_PURPOSES": "your-value",
"DATAPRISM_SECURITYPOLICY_ROLES_INVESTIGATOR": "your-value",
"DATAPRISM_PRIVACY_PROFILE": "your-value",
"DATAPRISM_PRIVACY_SCOPE_LIFETIME": "your-value",
"DATAPRISM_PRIVACY_HMAC_KEY_KEY_ID": "your-value",
"DATAPRISM_PRIVACY_HMAC_KEY_ENVIRONMENT_VARIABLE": "your-value",
"DATAPRISM_PRIVACY_HMAC_KEY_PROVIDER_REFERENCE": "your-value",
"DATAPRISM_AUDIT_SINK": "your-value",
"DATAPRISM_AUDIT_WRITER_ID": "your-value",
"DATAPRISM_AUDIT_FILE_PATH": "your-value",
"DATAPRISM_METRICS_SINK": "your-value",
"DATAPRISM_HAZELCAST_TOPOLOGY": "your-value",
"DATAPRISM_HAZELCAST_CLUSTERNAME": "your-value",
"DATAPRISM_HAZELCAST_JOIN_MODE": "your-value",
"DATAPRISM_HAZELCAST_JOIN_MEMBERS": "your-value",
"DATAPRISM_HAZELCAST_MEMBER_PORT": "your-value",
"DATAPRISM_OPERATOR_ENABLED": "your-value",
"DATAPRISM_OPERATOR_PORT": "your-value",
"DATAPRISM_OPERATOR_REQUIREDAUDIENCE": "your-value",
"DATAPRISM_OPERATOR_REQUIREDSCOPE": "your-value",
"DATAPRISM_SOURCES_CUSTOMER_BASE_URL": "your-value",
"DATAPRISM_SOURCES_CUSTOMER_TIMEOUT": "your-value"
}
}
}
}Run this in your terminal
claude mcp add data-prism --env LOADER_PATH=your-value --env DATAPRISM_SECURITY_JWT_ISSUER=your-value --env DATAPRISM_SECURITY_JWT_AUDIENCE=your-value --env DATAPRISM_SECURITY_JWT_JWK_SET_URI=your-value --env DATAPRISM_SECURITY_JWT_ISSUER_DISCOVERY_URI=your-value --env DATAPRISM_SECURITY_CALLER_CLAIMS_PRINCIPAL=your-value --env DATAPRISM_SECURITY_CALLER_CLAIMS_ROLES=your-value --env DATAPRISM_SECURITY_CALLER_CLAIMS_INVESTIGATION=your-value --env DATAPRISM_SECURITY_POLICY_PURPOSES=your-value --env DATAPRISM_SECURITYPOLICY_ROLES_INVESTIGATOR=your-value --env DATAPRISM_PRIVACY_PROFILE=your-value --env DATAPRISM_PRIVACY_SCOPE_LIFETIME=your-value --env DATAPRISM_PRIVACY_HMAC_KEY_KEY_ID=your-value --env DATAPRISM_PRIVACY_HMAC_KEY_ENVIRONMENT_VARIABLE=your-value --env DATAPRISM_PRIVACY_HMAC_KEY_PROVIDER_REFERENCE=your-value --env DATAPRISM_AUDIT_SINK=your-value --env DATAPRISM_AUDIT_WRITER_ID=your-value --env DATAPRISM_AUDIT_FILE_PATH=your-value --env DATAPRISM_METRICS_SINK=your-value --env DATAPRISM_HAZELCAST_TOPOLOGY=your-value --env DATAPRISM_HAZELCAST_CLUSTERNAME=your-value --env DATAPRISM_HAZELCAST_JOIN_MODE=your-value --env DATAPRISM_HAZELCAST_JOIN_MEMBERS=your-value --env DATAPRISM_HAZELCAST_MEMBER_PORT=your-value --env DATAPRISM_OPERATOR_ENABLED=your-value --env DATAPRISM_OPERATOR_PORT=your-value --env DATAPRISM_OPERATOR_REQUIREDAUDIENCE=your-value --env DATAPRISM_OPERATOR_REQUIREDSCOPE=your-value --env DATAPRISM_SOURCES_CUSTOMER_BASE_URL=your-value --env DATAPRISM_SOURCES_CUSTOMER_TIMEOUT=your-value -- docker run -i --rm -e LOADER_PATH -e DATAPRISM_SECURITY_JWT_ISSUER -e DATAPRISM_SECURITY_JWT_AUDIENCE -e DATAPRISM_SECURITY_JWT_JWK_SET_URI -e DATAPRISM_SECURITY_JWT_ISSUER_DISCOVERY_URI -e DATAPRISM_SECURITY_CALLER_CLAIMS_PRINCIPAL -e DATAPRISM_SECURITY_CALLER_CLAIMS_ROLES -e DATAPRISM_SECURITY_CALLER_CLAIMS_INVESTIGATION -e DATAPRISM_SECURITY_POLICY_PURPOSES -e DATAPRISM_SECURITYPOLICY_ROLES_INVESTIGATOR -e DATAPRISM_PRIVACY_PROFILE -e DATAPRISM_PRIVACY_SCOPE_LIFETIME -e DATAPRISM_PRIVACY_HMAC_KEY_KEY_ID -e DATAPRISM_PRIVACY_HMAC_KEY_ENVIRONMENT_VARIABLE -e DATAPRISM_PRIVACY_HMAC_KEY_PROVIDER_REFERENCE -e DATAPRISM_AUDIT_SINK -e DATAPRISM_AUDIT_WRITER_ID -e DATAPRISM_AUDIT_FILE_PATH -e DATAPRISM_METRICS_SINK -e DATAPRISM_HAZELCAST_TOPOLOGY -e DATAPRISM_HAZELCAST_CLUSTERNAME -e DATAPRISM_HAZELCAST_JOIN_MODE -e DATAPRISM_HAZELCAST_JOIN_MEMBERS -e DATAPRISM_HAZELCAST_MEMBER_PORT -e DATAPRISM_OPERATOR_ENABLED -e DATAPRISM_OPERATOR_PORT -e DATAPRISM_OPERATOR_REQUIREDAUDIENCE -e DATAPRISM_OPERATOR_REQUIREDSCOPE -e DATAPRISM_SOURCES_CUSTOMER_BASE_URL -e DATAPRISM_SOURCES_CUSTOMER_TIMEOUT ghcr.io/aindriub/data-prism-server:0.7.1Fill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"data-prism": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"LOADER_PATH",
"-e",
"DATAPRISM_SECURITY_JWT_ISSUER",
"-e",
"DATAPRISM_SECURITY_JWT_AUDIENCE",
"-e",
"DATAPRISM_SECURITY_JWT_JWK_SET_URI",
"-e",
"DATAPRISM_SECURITY_JWT_ISSUER_DISCOVERY_URI",
"-e",
"DATAPRISM_SECURITY_CALLER_CLAIMS_PRINCIPAL",
"-e",
"DATAPRISM_SECURITY_CALLER_CLAIMS_ROLES",
"-e",
"DATAPRISM_SECURITY_CALLER_CLAIMS_INVESTIGATION",
"-e",
"DATAPRISM_SECURITY_POLICY_PURPOSES",
"-e",
"DATAPRISM_SECURITYPOLICY_ROLES_INVESTIGATOR",
"-e",
"DATAPRISM_PRIVACY_PROFILE",
"-e",
"DATAPRISM_PRIVACY_SCOPE_LIFETIME",
"-e",
"DATAPRISM_PRIVACY_HMAC_KEY_KEY_ID",
"-e",
"DATAPRISM_PRIVACY_HMAC_KEY_ENVIRONMENT_VARIABLE",
"-e",
"DATAPRISM_PRIVACY_HMAC_KEY_PROVIDER_REFERENCE",
"-e",
"DATAPRISM_AUDIT_SINK",
"-e",
"DATAPRISM_AUDIT_WRITER_ID",
"-e",
"DATAPRISM_AUDIT_FILE_PATH",
"-e",
"DATAPRISM_METRICS_SINK",
"-e",
"DATAPRISM_HAZELCAST_TOPOLOGY",
"-e",
"DATAPRISM_HAZELCAST_CLUSTERNAME",
"-e",
"DATAPRISM_HAZELCAST_JOIN_MODE",
"-e",
"DATAPRISM_HAZELCAST_JOIN_MEMBERS",
"-e",
"DATAPRISM_HAZELCAST_MEMBER_PORT",
"-e",
"DATAPRISM_OPERATOR_ENABLED",
"-e",
"DATAPRISM_OPERATOR_PORT",
"-e",
"DATAPRISM_OPERATOR_REQUIREDAUDIENCE",
"-e",
"DATAPRISM_OPERATOR_REQUIREDSCOPE",
"-e",
"DATAPRISM_SOURCES_CUSTOMER_BASE_URL",
"-e",
"DATAPRISM_SOURCES_CUSTOMER_TIMEOUT",
"ghcr.io/aindriub/data-prism-server:0.7.1"
],
"env": {
"LOADER_PATH": "your-value",
"DATAPRISM_SECURITY_JWT_ISSUER": "your-value",
"DATAPRISM_SECURITY_JWT_AUDIENCE": "your-value",
"DATAPRISM_SECURITY_JWT_JWK_SET_URI": "your-value",
"DATAPRISM_SECURITY_JWT_ISSUER_DISCOVERY_URI": "your-value",
"DATAPRISM_SECURITY_CALLER_CLAIMS_PRINCIPAL": "your-value",
"DATAPRISM_SECURITY_CALLER_CLAIMS_ROLES": "your-value",
"DATAPRISM_SECURITY_CALLER_CLAIMS_INVESTIGATION": "your-value",
"DATAPRISM_SECURITY_POLICY_PURPOSES": "your-value",
"DATAPRISM_SECURITYPOLICY_ROLES_INVESTIGATOR": "your-value",
"DATAPRISM_PRIVACY_PROFILE": "your-value",
"DATAPRISM_PRIVACY_SCOPE_LIFETIME": "your-value",
"DATAPRISM_PRIVACY_HMAC_KEY_KEY_ID": "your-value",
"DATAPRISM_PRIVACY_HMAC_KEY_ENVIRONMENT_VARIABLE": "your-value",
"DATAPRISM_PRIVACY_HMAC_KEY_PROVIDER_REFERENCE": "your-value",
"DATAPRISM_AUDIT_SINK": "your-value",
"DATAPRISM_AUDIT_WRITER_ID": "your-value",
"DATAPRISM_AUDIT_FILE_PATH": "your-value",
"DATAPRISM_METRICS_SINK": "your-value",
"DATAPRISM_HAZELCAST_TOPOLOGY": "your-value",
"DATAPRISM_HAZELCAST_CLUSTERNAME": "your-value",
"DATAPRISM_HAZELCAST_JOIN_MODE": "your-value",
"DATAPRISM_HAZELCAST_JOIN_MEMBERS": "your-value",
"DATAPRISM_HAZELCAST_MEMBER_PORT": "your-value",
"DATAPRISM_OPERATOR_ENABLED": "your-value",
"DATAPRISM_OPERATOR_PORT": "your-value",
"DATAPRISM_OPERATOR_REQUIREDAUDIENCE": "your-value",
"DATAPRISM_OPERATOR_REQUIREDSCOPE": "your-value",
"DATAPRISM_SOURCES_CUSTOMER_BASE_URL": "your-value",
"DATAPRISM_SOURCES_CUSTOMER_TIMEOUT": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"data-prism": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"LOADER_PATH",
"-e",
"DATAPRISM_SECURITY_JWT_ISSUER",
"-e",
"DATAPRISM_SECURITY_JWT_AUDIENCE",
"-e",
"DATAPRISM_SECURITY_JWT_JWK_SET_URI",
"-e",
"DATAPRISM_SECURITY_JWT_ISSUER_DISCOVERY_URI",
"-e",
"DATAPRISM_SECURITY_CALLER_CLAIMS_PRINCIPAL",
"-e",
"DATAPRISM_SECURITY_CALLER_CLAIMS_ROLES",
"-e",
"DATAPRISM_SECURITY_CALLER_CLAIMS_INVESTIGATION",
"-e",
"DATAPRISM_SECURITY_POLICY_PURPOSES",
"-e",
"DATAPRISM_SECURITYPOLICY_ROLES_INVESTIGATOR",
"-e",
"DATAPRISM_PRIVACY_PROFILE",
"-e",
"DATAPRISM_PRIVACY_SCOPE_LIFETIME",
"-e",
"DATAPRISM_PRIVACY_HMAC_KEY_KEY_ID",
"-e",
"DATAPRISM_PRIVACY_HMAC_KEY_ENVIRONMENT_VARIABLE",
"-e",
"DATAPRISM_PRIVACY_HMAC_KEY_PROVIDER_REFERENCE",
"-e",
"DATAPRISM_AUDIT_SINK",
"-e",
"DATAPRISM_AUDIT_WRITER_ID",
"-e",
"DATAPRISM_AUDIT_FILE_PATH",
"-e",
"DATAPRISM_METRICS_SINK",
"-e",
"DATAPRISM_HAZELCAST_TOPOLOGY",
"-e",
"DATAPRISM_HAZELCAST_CLUSTERNAME",
"-e",
"DATAPRISM_HAZELCAST_JOIN_MODE",
"-e",
"DATAPRISM_HAZELCAST_JOIN_MEMBERS",
"-e",
"DATAPRISM_HAZELCAST_MEMBER_PORT",
"-e",
"DATAPRISM_OPERATOR_ENABLED",
"-e",
"DATAPRISM_OPERATOR_PORT",
"-e",
"DATAPRISM_OPERATOR_REQUIREDAUDIENCE",
"-e",
"DATAPRISM_OPERATOR_REQUIREDSCOPE",
"-e",
"DATAPRISM_SOURCES_CUSTOMER_BASE_URL",
"-e",
"DATAPRISM_SOURCES_CUSTOMER_TIMEOUT",
"ghcr.io/aindriub/data-prism-server:0.7.1"
],
"env": {
"LOADER_PATH": "your-value",
"DATAPRISM_SECURITY_JWT_ISSUER": "your-value",
"DATAPRISM_SECURITY_JWT_AUDIENCE": "your-value",
"DATAPRISM_SECURITY_JWT_JWK_SET_URI": "your-value",
"DATAPRISM_SECURITY_JWT_ISSUER_DISCOVERY_URI": "your-value",
"DATAPRISM_SECURITY_CALLER_CLAIMS_PRINCIPAL": "your-value",
"DATAPRISM_SECURITY_CALLER_CLAIMS_ROLES": "your-value",
"DATAPRISM_SECURITY_CALLER_CLAIMS_INVESTIGATION": "your-value",
"DATAPRISM_SECURITY_POLICY_PURPOSES": "your-value",
"DATAPRISM_SECURITYPOLICY_ROLES_INVESTIGATOR": "your-value",
"DATAPRISM_PRIVACY_PROFILE": "your-value",
"DATAPRISM_PRIVACY_SCOPE_LIFETIME": "your-value",
"DATAPRISM_PRIVACY_HMAC_KEY_KEY_ID": "your-value",
"DATAPRISM_PRIVACY_HMAC_KEY_ENVIRONMENT_VARIABLE": "your-value",
"DATAPRISM_PRIVACY_HMAC_KEY_PROVIDER_REFERENCE": "your-value",
"DATAPRISM_AUDIT_SINK": "your-value",
"DATAPRISM_AUDIT_WRITER_ID": "your-value",
"DATAPRISM_AUDIT_FILE_PATH": "your-value",
"DATAPRISM_METRICS_SINK": "your-value",
"DATAPRISM_HAZELCAST_TOPOLOGY": "your-value",
"DATAPRISM_HAZELCAST_CLUSTERNAME": "your-value",
"DATAPRISM_HAZELCAST_JOIN_MODE": "your-value",
"DATAPRISM_HAZELCAST_JOIN_MEMBERS": "your-value",
"DATAPRISM_HAZELCAST_MEMBER_PORT": "your-value",
"DATAPRISM_OPERATOR_ENABLED": "your-value",
"DATAPRISM_OPERATOR_PORT": "your-value",
"DATAPRISM_OPERATOR_REQUIREDAUDIENCE": "your-value",
"DATAPRISM_OPERATOR_REQUIREDSCOPE": "your-value",
"DATAPRISM_SOURCES_CUSTOMER_BASE_URL": "your-value",
"DATAPRISM_SOURCES_CUSTOMER_TIMEOUT": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
DATAPRISM_SECURITY_JWT_ISSUER_DISCOVERY_URI envDATAPRISM_PRIVACY_HMAC_KEY_PROVIDER_REFERENCE envDATAPRISM_AUDIT_FILE_PATH envDATAPRISM_HAZELCAST_CLUSTERNAME envDATAPRISM_HAZELCAST_JOIN_MODE envDATAPRISM_HAZELCAST_JOIN_MEMBERS envDATAPRISM_HAZELCAST_MEMBER_PORT envDATAPRISM_OPERATOR_ENABLED envDATAPRISM_OPERATOR_PORT envDATAPRISM_OPERATOR_REQUIREDAUDIENCE envDATAPRISM_OPERATOR_REQUIREDSCOPE envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified with the GitHub account AindriuB, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: LOADER_PATH, DATAPRISM_SECURITY_JWT_ISSUER, DATAPRISM_SECURITY_JWT_AUDIENCE, DATAPRISM_SECURITY_JWT_JWK_SET_URI, DATAPRISM_SECURITY_CALLER_CLAIMS_PRINCIPAL, DATAPRISM_SECURITY_CALLER_CLAIMS_ROLES, DATAPRISM_SECURITY_CALLER_CLAIMS_INVESTIGATION, DATAPRISM_SECURITY_POLICY_PURPOSES, DATAPRISM_SECURITYPOLICY_ROLES_INVESTIGATOR, DATAPRISM_PRIVACY_PROFILE, DATAPRISM_PRIVACY_SCOPE_LIFETIME, DATAPRISM_PRIVACY_HMAC_KEY_KEY_ID, DATAPRISM_PRIVACY_HMAC_KEY_ENVIRONMENT_VARIABLE, DATAPRISM_AUDIT_SINK, DATAPRISM_AUDIT_WRITER_ID, DATAPRISM_METRICS_SINK, DATAPRISM_HAZELCAST_TOPOLOGY, DATAPRISM_SOURCES_CUSTOMER_BASE_URL, DATAPRISM_SOURCES_CUSTOMER_TIMEOUT
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.7.1) reached the registry 15 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Docker on your computer.
In the same category: Context7, Codebase Memory, Exa
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Fail-closed privacy layer that pseudonymises enterprise API data for LLM agents and MCP clients.
Data Prism is an open-source privacy layer for Java/Spring teams putting LLM agents or MCP clients in front of internal APIs holding customer data. It pseudonymises personal data per privacy scope, refuses anything unclassified, and can keep a hash-chained audit trail.
What it is. A privacy enforcement layer for enterprise AI. It gives LLM agents useful, correlated business context — one consistent synthetic identity per entity within a privacy scope — while controlling which personal data crosses the AI boundary, and in what form.
Who it's for. Java/Spring platform and backend teams putting LLM agents or MCP clients in front of internal APIs that hold customer data. If nothing you run exposes personal data to a model, you don't need this.
Status: the walking skeleton and every slice through S9a are built, with 18 Maven submodules (19 Maven projects in the reactor counting the root pom-packaged aggregator itself) and a passing test suite. The privacy engine, correlation and consistency findings, parallel mTLS connectors, an embedded Hazelcast identity cache and read budget (shared only across members that have joined one cluster; see multiple instances), an OAuth2 resource server with session-derived PrivacyContext, audit and metrics are all real and exercised end to end. The standalone server is the primary deployment surface; the Spring Boot starter is the embedded option. A one-command local Compose quickstart also exists: see "Try it" below. Two MCP tools ship today, get_entity_context and compare_entity_sources — the other two named in the design review, search_entity_data and describe_entity_model, are not yet built (docs/tools.md "Not yet built"). A durable, append-only, hash-chained audit sink and an offline AuditChainVerifier ship as of 0.3.0, opt-in via dataprism.audit.sink: hash-chained; the verifier catches an edit or deletion inside a writer's chain, but cannot detect truncation of a writer's most recent records or the deletion of a whole process boot's records, and the trail does not resist an operator, or anyone else, who already has write access to the file (docs/audit.md "What this does and does not prove"). Not built: the re-identification operator surface (deferred past V1 by decision, see docs/architecture.md#decisions-worth-knowing) and the Elasticsearch connector and its search tools. See docs/plan/PLAN.md for what is open.
An organisation wants an LLM to investigate live business data spread across several systems. Giving the model direct API access is not acceptable: those APIs carry personal and confidential data, each system represents the same entity differently, and raw identifiers let anything downstream correlate across sessions.
The obvious fix — redact everything sensitive — destroys the investigation. Once three systems' names for one person are all [REDACTED], the model cannot tell whether it is looking at one person or three.
It sits between the two and does two things that are easy to confuse:
It makes identity consistent. One subject gets one synthetic identity across every source, derived deterministically from (scope, subject, namespace, algorithm version, key) — never random, never stored in plaintext, and reproducible without the cache. The same person in three systems reads as one person to the model.
It leaves the data inconsistent, and says so. If those three systems disagree about a name, the answer carries a finding that says they disagree. The platform never makes enterprise data look cleaner than it is. That distinction is the point of the project:
Identity representation becomes consistent. Underlying data inconsistencies
become *more* visible, not less.
Pseudonyms are scoped. The same person in two different investigations gets two different synthetic identities, so nothing correlates across cases by accident.
Not an API gateway, not an ETL platform, not a master-data system, not an identity provider, and not an entity-resolution engine — correlation requires a key the sources already share, behind a documented SPI. It carries no business domain: no Customer, Taxpayer or Employee type exists outside the example application.
It is not anonymisation. Under GDPR Art. 4(5), pseudonymised data is still personal data. Sending Data Prism output to a third-party model is still processing, and still needs a lawful basis, a DPIA, and a transfer mechanism where the provider is outside the EU. The platform reduces exposure; it does not remove the obligation.
The fastest way to see a real MCP call answered by the real privacy engine — no local JDK, no Maven install, one command:
docker compose up
pulls the published ghcr.io/aindriub/data-prism-quickstart- images (pin one with QUICKSTART_IMAGE_TAG=0.7.0; run docker compose -f compose.yaml -f compose.build.yaml up --build instead to build every image from source) and brings up the standalone server, a synthetic fixture API and a local HTTPS JWT issuer, proving an agent-compatible get_entity_context call returns a pseudonymised response. Walk through it in docs/quickstart.md; connect your own agent client to either that stack or a real deployment via docs/agents/.
Once you have seen the demo, protect your own API: docs/quickstart.md ends with a "What next" section pointing at docs/protect-your-own-api.md, a YAML-only walkthrough from a real JSON REST API to a working get_entity_context call.
The ghcr.io/aindriub/data-prism-server image listed there is published as a multi-architecture manifest list covering linux/amd64 and linux/arm64, each built and verified natively — docker run on Apple Silicon or any other arm64 host pulls the arm64 image directly, no emulation required.
It is not a one-command install, on either architecture. docker run alone yields a server that refuses to start: DataPrismContractValidator demands a reviewed DataSourceAdapter bean for every configured source, and DataPrismProperties.validate() demands a full deployment configuration (JWT issuer/audience/JWKS, caller-claim mappings, security policy, HMAC key reference, audit sink, metrics sink, Hazelcast topology). Neither ships in the image. Two things an operator must supply themselves before it serves anything:
dataprism.* vocabulary.docs/configuration.md is the authoritative, complete contract for both. The "Try it" section above is a local Compose fixture for evaluation, not this image or that configuration.
The full set of user docs is also published, rendered and searchable, at https://aindriub.github.io/data-prism/.
Each row links the site page and the repo file it is built from.
| Doc | Site | What it covers |
|---|---|---|
docs/quickstart.md | quickstart/ | One-command local Compose demonstration — start here |
docs/protect-your-own-api.md | protect-your-own-api/ | Pointing Data Prism at your own API instead of the fixture |
docs/configuration.md | configuration/ | The authoritative, complete dataprism.* deployment configuration contract |
docs/tools.md | tools/ | What each shipped MCP tool takes and returns, worked examples |
docs/extending.md | extending/ | Protecting a new source: a reviewed Java adapter, or the configuration-driven JSON REST mode |
docs/audit.md | audit/ | What the hash-chained audit trail records, and how to verify it |
docs/architecture.md | architecture/ | Module map, dependency rules, the boundaries that must not be crossed, dated decisions |
docs/agents/ | agents/ | Connecting an MCP agent client, local fixture or authenticated remote |
docs/agents/stdio.md | agents/stdio/ | The local stdio fixture workflow: a real MCP tool call with no JWT, network call or source system |
docs/agents/remote-http.md | agents/remote-http/ | The authenticated Streamable HTTP workflow against a real MCP endpoint; no development bypass |
docs/faq.md | faq/ | Direct answers on pseudonymisation, PII detection, Java requirements, the audit trail and prompt injection |
docs/comparison.md | comparison/ | How Data Prism compares to Presidio, LLM Guard, NeMo Guardrails and MCP gateways or proxies |
docs/use-cases/pseudonymise-customer-data-spring-boot.md | use-cases/pseudonymise-customer-data-spring-boot/ | Pseudonymising customer data from a Spring Boot API before an LLM agent sees it |
docs/use-cases/gdpr-data-minimisation-mcp.md | use-cases/gdpr-data-minimisation-mcp/ | GDPR data minimisation for MCP tools |
docs/use-cases/consistent-pseudonyms-across-systems.md | use-cases/consistent-pseudonyms-across-systems/ | Keeping one customer recognisable across systems without exposing identity |
CHANGELOG.md | changelog/ | Every notable Data Prism change by version, in Keep a Changelog format |
Not published on the site.
| Doc | What it covers |
|---|---|
docs/design-review.md | Amendments to the specification, with reasoning. Authoritative |
docs/development-plan.md | Slice order, sizing, and the decisions that block the first one |
docs/pack.md | The original specification. Superseded and historical; describes tools that were never built |
| [docs/conventions.md](docs/conventio
Only the beginning is shown; read the rest in the repo