dazai — burn-after-reading secret (motokano)

io.github.New1DirectionPublished by GitHub account New1Directionv0.1.0Updated Oct 24, 2026

Serve a secret to an agent exactly N times from locked RAM, then wipe it and self-destruct.

VerifiedSTDIODesktop onlyDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

A local MCP server that hands a secret to an agent a set number of times from locked RAM, then wipes it and kills itself.

What you can do
  • Serve a pre-loaded secret value to an agent a fixed number of times, then wipe it from locked memory and terminate the process.
  • Register an agent's process ID with a watchdog daemon so it is killed when the shell or SSH session ends.
  • Run a heartbeat client that ties the daemon's lifetime to a terminal session.
  • Optionally append fixed-vocabulary lifecycle records (arm, read, wipe, kill) to a tamper-evident ledger file.
When to use it
Use it when an agent needs a credential for a single task and you want the plaintext to disappear afterwards, or when you want agents to die automatically when your session ends. It is aimed at people who already keep secrets in MCP configs and want a smaller exposure window.
Requirements
Runs as a local process over stdio on macOS or Linux; prebuilt binaries cover macOS arm64/x86_64 and Linux x86_64/arm64, or build from source with Cargo. The seccomp-confined daemon is a from-source Linux build needing libseccomp-dev and pkg-config. Secrets are passed as command-line tool definitions, and no environment variables or headers are declared.
Before you install
Secrets are supplied on the command line, so they may be visible in process listings or shell history. The project states it does not protect against GPU VRAM copies, exec-tool stdout, privileged or same-UID attackers on the live machine, cold-boot or DMA attacks, or a hard crash where the wipe cannot run. The daemon can SIGKILL registered processes, so arm it deliberately; it runs in dry-run mode unless armed.

Installation

In SourceWeft

  1. Open dazai — burn-after-reading secret (motokano) in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

ningen-shikkaku

[CI] [docs] [License: MIT]

Burn-after-reading secrets for AI agents.

ningen-shikkaku ships two small Rust binaries — dazai (the session-bound daemon) and motokano (a self-immolating one-shot MCP server).

Your MCP configs are full of plaintext API keys, and every agent you run can read all of them — and they keep working long after the agent is done. dazai inverts that: secrets live in locked, non-swappable RAM, are served to agents over MCP, and are destroyed after N reads — or the instant your session dies.

[burn-after-reading demo]

bash
motokano --calls 1 --tool 'name=get_key,kind=static,value=s3cr3t' --arm

Point any MCP client at it and call get_key once → you receive s3cr3t → the server wipes the value out of locked memory and SIGKILLs itself. Call again → the process is gone.

Install

bash
# prebuilt binaries (macOS arm64/x86_64, Linux x86_64/arm64)curl --proto '=https' --tlsv1.2 -LsSf https://github.com/New1Direction/ningen-shikkaku/releases/latest/download/dazai-installer.sh | sh
# or homebrewbrew install New1Direction/tap/dazai New1Direction/tap/motokano
# or from source (required for the Linux seccomp build)git clone https://github.com/New1Direction/ningen-shikkakucd ningen-shikkaku/rscargo build --release                       # -> target/release/{dazai, motokano}cargo build --release --features seccomp    # Linux: seccomp syscall allowlist

Prebuilt binaries are built with default features; the seccomp-confined daemon is a from-source build (it links libseccomp — install libseccomp-dev + pkg-config first).

Use it with Claude Code

bash
# a one-shot secret an agent can read exactly once:claude mcp add burn-once -- motokano --calls 1 --arm \  --tool 'name=get_key,kind=static,value=YOUR-SECRET'
# or the session-bound daemon: agents register their PID and get SIGKILLed# the moment your session diesdazai daemon --arm --grace 5 &claude mcp add dazai -- dazai mcp

Any MCP client works the same way — the transport is plain stdio.

And the second act: a dead-man's switch for your agents

The same daemon is a session kill-switch. Any MCP client registers its PID; when your shell/SSH session dies, your heartbeat stops, or a panic signal arrives, dazai SIGKILLs every registered process, overwrites its secrets with a wipe the compiler can't optimize away, and exits. Walk away: agents die, secrets burn.

bash
dazai daemon --ping-timeout 15        # terminal A  (dry-run by default; --arm makes it real)dazai client --interval 5             # terminal B# close terminal B  ->  the daemon wipes its secrets and exits

It runs only on your own machine, on your own secrets and your own configured tools. It never touches another process, file, or host.

What's in the box

It ships in two layers:

  • a hardened Rust daemon + tooling — the real thing: mlock (no swap), madvise(MADV_DONTDUMP) + prctl(PR_SET_DUMPABLE, 0) (no core dumps / no ptrace), a seccomp syscall allowlist (no execve/open/connect/…), and a non-elidable explicit_bzero / memset_s wipe; and
  • a Python reference implementation — the original proof-of-concept that established the mechanism (see python-reference.md).
ComponentWhat it does
dazai daemonThe watchdog: holds mlock'd secrets + a UNIX-socket heartbeat; wipes and self-destructs on session loss. seccomp-confined on Linux.
dazai clientThe heartbeat client — ties the daemon's life to a shell / SSH session.
dazai mcpAn MCP server exposing the daemon as tools, so any agent can register its PID for session-bound protection (it gets SIGKILLed if your session dies).
motokanoA standalone self-immolating MCP server: serve N tool calls, then wipe secret state and exit.
Python referencesecmem.py / deadman.py / heartbeat.py / shellrc.sh — the portable proof-of-concept.

Architecture

mermaid
flowchart LR    A["MCP client / AI agent<br/>(stdio transport)"]
    subgraph Daemon["dazai daemon (kikka Watchdog)"]        D["dazai daemon<br/>mlock'd SecretBuffers (goodnight)<br/>seccomp-confined on Linux (kekkai)"]        SOCK[("UNIX socket 0600<br/>HELLO heartbeat + REGISTER / ARM / STATUS")]    end
    MCPD["dazai mcp<br/>(rei · rmcp server)"]    HB["dazai client<br/>(heartbeat: HELLO / PING)"]    MOTO["motokano<br/>(self-immolating MCP server)<br/>static values in SecretBuffer"]    KILL{{"wipe (explicit_bzero / memset_s)<br/>+ SIGKILL"}}
    A -->|"register pid / status / panic"| MCPD    A -->|"get_key (static, N reads)"| MOTO    MCPD -->|"relay verbs + signals via pidfile"| SOCK    HB -->|"holds liveness connection"| SOCK    SOCK --- D    MOTO -. "optional --dazai-socket: register + monitor" .-> SOCK    D ==>|"on trigger: SIGKILL registered PIDs, then wipe + self-SIGKILL"| KILL    MOTO ==>|"after N calls / EOF / daemon death: wipe + exit"| KILL    HB -. "drop / ping-timeout / panic signal" .-> D

Korg interop

dazai daemon and motokano can feed Korg's tamper-evident ledger: --korg-sink PATH (or /dev/fd/N for a pre-opened descriptor) appends one Korg append-shape record per arm, session, read, wipe and kill step. Records carry only fixed-vocabulary fields and counters. Secret values, lengths, digests, tool names, arguments, paths and the environment are never recorded. Korg imports the file through its ningen-shikkaku.lifecycle@v2 envelope profile and assigns sequence numbers, hashes and signatures. See Korg lifecycle records.

Threat model

daZai shrinks the window and the surface in which plaintext secrets are reachable, and makes session-end deterministically destroy them.

It protects against:

RiskHow
Secrets paged to swapmlock locks the buffers into RAM
Secrets captured in core dumpsmadvise(MADV_DONTDUMP) + prctl(PR_SET_DUMPABLE, 0) (Linux)
Session loss leaving secrets residentheartbeat drop / logout → wipe + SIGKILL
Secrets lingering in process memory after useexplicit_bzero / memset_s — a wipe the compiler may not elide
A confined process escapingseccomp allowlist denies execve / open / connect / ptrace / … (Linux)
ptrace snooping the daemonprctl(PR_SET_DUMPABLE, 0) (Linux)

It does NOT protect against (and the project is deliberately honest about this):

  • GPU VRAM. If an attached LLM/agent copies a secret into GPU memory, killing the host process does not wipe VRAM. daZai controls host RAM and the processes it supervises — not an accelerator's memory.
  • exec-tool stdout. motokano's kind=exec tools return a command's stdout, which is OS-buffered and not held in a locked buffer. Use kind=static (a pre-loaded, locked, wipeable value) when you need the wipe guarantee.
  • Managed-runtime residue (Python reference). CPython copies bytes freely, so a secret may transiently live in unlocked heap before/after the locked buffer. The Rust implementation eliminates this for its own buffers (data is written into the locked mapping and never copied to a GC heap); the Python tier is a reference, not a hard guarantee.
  • A privileged or same-UID attacker on the live box (root, /proc/<pid>/mem, a debugger) reading memory before the wipe. mlock stops swap, not memory reads; seccomp + PR_SET_DUMPABLE raise the bar on Linux, but an adversary who already has privileged access to your running machine is out of scope.
  • Cold-boot / DMA / physical attacks on RAM.
  • A hard crash (kernel OOM, an external kill -9, power loss): the wipe path can't run, so nothing is zeroed. The mechanism is best-effort on these paths and never claims otherwise.

In short: daZai is not, and cannot be, a guarantee against an attacker who already owns your running machine. It is a sharp tool for making secrets ephemeral and session-bound, with every limitation stated up front.

Verification

  • 81 tests across the Rust workspace (secure memory, the panic policy, the wire protocol, the MCP layer, the one-shot lifecycle, the Korg lifecycle contract) plus the 29-test Python reference.
  • Linux seccomp is validated on both architectures under the real KillProcess filter — aarch64 (locally) and x86_64 (CI) — where the daemon installs the live filter and the full integration suite runs against it with no SIGSYS.
  • Every push runs the whole suite (default and --features seccomp), clippy -D warnings, and rustfmt --check on x86_64 Linux as a permanent regression gate.

Deep technical docs (per-crate design, the seccomp allowlist, the adversarial-review history) live in rs/README.md; the Python proof-of-concept is in python-reference.md.

The name

Named for the novelist Osamu Dazai, whose work circles themes of disappearance and self-erasure — fitting for software whose defining act is to wipe itself out the moment it is no longer being watched over. The repository takes its name from his novel No Longer Human (人間失格, Ningen Shikkaku). It's flavor, not a manifesto; the software just self-destructs on cue.

License

MIT © 2026 New1Direction.

Source: README.md at commit f464356

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts