Pipelock MCP Server

<strong>Open-source AI agent firewall for Verifiable Egress Control.</strong>

Local serverstdioPython

What is the Pipelock MCP server?

Open-source AI agent firewall for Verifiable Egress Control.. Exposed over MCP by the pipelock mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

Its toolset

Everything the assistant can do here goes through one of these:

  • DLP — ** 65 built-in patterns for API keys, tokens, credentials, cryptocurrency keys, environment secrets, and financial identifiers with checksum
  • Skill — file scanning:** pipelock skill-scan inventories agent skill files, compares them to an operator-owned lock file, and flags source-to-sink
  • Mode — Security
  • strict — Allowlist-only
  • balanced — Blocks naive + detects sophisticated
  • audit — Logging only
  • Threat — Coverage
  • Comparison — Canonical comparison hub: AI runtime security comparison
  • Containment — Unprivileged process containment uses OS-native primitives. Linux uses Landlock, seccomp, and network namespaces. macOS uses sandbox-exec profiles

Configuration

You will need one environment variable: PROVIDER_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Adding it to your client

Installation goes through your MCP client rather than a global install: point it at @modelcontextprotocol/server-filesystem on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

When to reach for it

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Pipelock's toolset — DLP, Skill, Mode and 6 more — is a fair guide to whether it matches your workflow. It is maintained by luckypipewrench; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Pipelock's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 9 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Pipelock.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the pipelock mcp server does with a few real requests.

Available tools

ToolWhat it does
DLP** 65 built-in patterns for API keys, tokens, credentials, cryptocurrency keys, environment secrets, and financial identifiers with checksum validation. BIP-39 seed phrase detection uses dictionary lookup, sliding window
Skillfile scanning:** pipelock skill-scan inventories agent skill files, compares them to an operator-owned lock file, and flags source-to-sink combinations such as credential-to-network-sink or shell-to-write with line evide
ModeSecurity
strictAllowlist-only
balancedBlocks naive + detects sophisticated
auditLogging only
ThreatCoverage
ComparisonCanonical comparison hub: [AI runtime security comparison](https://pipelab.org/compare/)
ContainmentUnprivileged process containment uses OS-native primitives. Linux uses Landlock, seccomp, and network namespaces. macOS uses sandbox-exec profiles. In containers, --best-effort keeps Landlock and seccomp when namespace c

How to install the Pipelock MCP server

{
  "mcpServers": {
    "pipelock": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem"],
      "env": {
        "PROVIDER_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
PROVIDER_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Pipelock to DLP.
  • Use Pipelock to Skill.
  • Use Pipelock to Mode.

Frequently asked questions

It connects Pipelock to MCP-compatible AI assistants such as Claude and Cursor, exposing 9 tools (DLP, Skill, Mode, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Pipelock directly.