Book a Demo

Privacy Code Scanner

Free on GitHub. Code-based evidence for GDPR data mapping and RoPA, at development speed.

Free on GitHub. ProtoMap is a context engine and model harness for gRPC and Protobuf. It maps every service, message, and field across your organization’s code, updates with every commit, and needs no AI tokens.

ProtoMap See it in Action Benchmarks CI Integrations MCP Servers

Privacy Code Scanner See it in Action Data Flow Mapping Privacy Impact Assessment Records of Processing Activities CI Integrations

For Engineering

Service Catalog & API Context AI Coding Agent Context

For Privacy & Compliance

GDPR Data Mapping, RoPA, PIA & DPIA Privacy by Design for Developers AI Governance & Shadow AI Discovery Third-Party Data Flow Monitoring

For Data Security

Data Minimization & Leak Prevention

Customers How It Works ROI Calculator Events Newsroom About Us Blog Collateral & Webinars ProtoMap Docs Privacy Docs HoundDog.ai vs. Privado

Pricing

Sign In Contact Us

Book a Demo Start Free

Video · MozFest 2026

ProtoMap, live at MozFest

A talk and live demo from MozFest’s Open Source House: why coding agents spend tokens rediscovering gRPC dependencies, and how ProtoMap gives them that context instead.

Video · 10:53
Open Source House, MozFest
October 29, 2026

The problem

Asked what a change to a service, method, or field breaks, a coding agent spends minutes and tokens rediscovering dependencies. Protobuf files list the APIs but not who calls them, and the agent sees only the repositories checked out on the machine.

The solution

ProtoMap is a context engine and model harness for gRPC and Protobuf. It computes those dependencies from source code across every repository. Engineers query it in plain English; coding agents query it over MCP.

reduction in tokens and time for change-planning tasks.: 8×; Enterprise customer · multi-million-line monorepo
AI tokens to build the context, which updates with every commit.: 0; Standard CPU runners in your CI

In this video

Chapters

01 Introduction
02 The problem: AI coding agents rediscover dependencies
03 ProtoMap: a context engine
04 Live demo
05 Callers and callees
06 Which services depend on ClinicalEncounterCoordination?
07 Blast radius of changing a field name
08 Benchmarks: Claude Code with and without the ProtoMap MCP server
09 Wrap-up

Keep exploring

Benchmarks and a side-by-side run

7.7× faster 6.4× cheaper 9 gRPC repositories · 5M lines Benchmarks

ProtoMap benchmarks

Claude Code with and without the ProtoMap MCP server, graded against an answer key that does not come from ProtoMap.

See the benchmarks Claude Code v2.1.312 · Opus 5.5 with high effort~/protomap-test> Find every caller of RPC acme.documents.v1.ResolveDocuments in every repo that calls it, including indirect calls through strings, registries, or reflection, and give the calling service for each.● Searching for ResolveDocuments|resolveDocuments● Listed 1 directory, called protomap 2 times● ProtoMap reports 18 call sites. I'll check them with a text search of the local checkout.● Read 14 files, searched 6 patternsClaude Code v2.1.312 · Opus 5.5 with high effort~/protomap-test> Find every caller of RPC acme.documents.v1.ResolveDocuments in every repo that calls it, including indirect calls through strings, registries, or reflection, and give the calling service for each.● Searching for ResolveDocuments|resolveDocuments● Listed 1 directory, called protomap 2 times● ProtoMap reports 18 call sites. I'll check them with a text search of the local checkout.● Read 14 files, searched 6 patterns

HoundDog.ai Benchmarks · Side by side ProtoMap × Claude Code 7× faster · 36× cheaper Claude Code alone6:01 · $14.44 Claude Code + ProtoMap0:50 · $0.40 Video · 1:09

ProtoMap × Claude Code, side by side

Two live Claude Code sessions given the same prompt: ProtoMap's answers in 50 seconds for $0.40, the baseline's in 6 minutes for $14.44.

Watch the video

Try it on your code.

Install the self-hosted version for free. It runs on your machine with Docker, and your source code stays in your environment.

Book a Demo Start Free

Paste into your coding agent

Set up ProtoMap and show me what it can do. ProtoMap maps gRPC services and protobuf messages across repositories, and gives coding agents that graph over MCP. Docs: https://docs.protomap.ai/quickstart/

Tell me what you are about to do before each step that installs something.

1. Check that this computer has git, Docker with Compose 2.23.1 or newer, at least 4 GB of RAM, and 20 GB of disk space. If anything is missing, tell me and stop.

2. Install ProtoMap Server, in a folder outside this repository:

git clone https://github.com/hounddogai/protomap.git
cd protomap
./self-hosted/scripts/install.sh

The installer asks questions. Choose Trial, which runs PostgreSQL locally and logs the CLI in, and keep the default port.

3. Show me the address and the one-time setup key the installer prints. Ask me to open the address, enter the key, and create my organization and owner account. Wait until I say that's done.

4. Scan this repository, from a new shell so the CLI is on the PATH:

protomap scan .

If it has no gRPC services in a supported language, tell me, and offer to scan a public example instead:

git clone https://github.com/GoogleCloudPlatform/microservices-demo.git
protomap scan microservices-demo

5. From the scanned repository's folder, add ProtoMap to yourself as an MCP server:

Claude Code: claude mcp add protomap -- protomap mcp serve
Codex: codex mcp add protomap -- protomap mcp serve
Antigravity: add "protomap": { "command": "protomap", "args": ["mcp", "serve"] } under mcpServers in ~/.gemini/config/mcp_config.json
Others: https://docs.protomap.ai/coding-agents/

Tell me if I need to restart you for it to take effect.

6. Tell me what the scan found, then use ProtoMap's tools to answer one question about my services, such as which services call a method and where. Suggest two more questions I could ask.