DeadBolt MCP server
Commit Nov 15, 2026Acts as a local execution gate for software agents to enforce policies, operator controls, and fixed deadlines on tool actions.
Also known as seanebones-lang/deadbolt, deadbolt
- Stars
- 5
- Tools
- 2
- Downloads, 30 days
- —
- Latest version
- 2.0.2
- Last commit
- Nov 15, 2026
- License
- Apache-2.0
What is DeadBolt MCP?
DeadBolt acts as a local execution gate for software agents to enforce policies, operator controls, and fixed deadlines on tool actions. It exposes 2 tools, such as deadbolt_get_integration_guide, deadbolt_check_bundle.
Summary generated from the project's README
About DeadBolt MCP server
DeadBolt serves as a local execution gate designed to protect software agents by enforcing strict policies and operator controls. It acts as a checkpoint between an AI agent and the actual execution of a tool, ensuring that actions comply with predefined rules, spend caps, and fixed deadlines. Developers can integrate this security layer into Rust applications, Python environments, or by wrapping existing stdio MCP servers using the mcp-proxy command.
This system operates locally and does not require a model account, API key, or cloud service to function. Users can deploy it as an embedded library in Rust, a local sidecar for Python or Node applications, or as a verified local bundle for desktop MCP clients. It provides granular control through tool and destination policies, allowing operators to pause execution, set idle timeouts, or kill active runs. By placing the gate at the point of effect, it ensures that a denial prevents the underlying function from ever being called.
What you can do with it
- 1Enforce tool execution policiesA developer can prevent an agent from running unauthorized actions by wrapping tool calls in a dispatch function that checks against a policy.
- 2Apply fixed run deadlinesYou can ensure that an agentic task does not run indefinitely by enforcing a specific time limit on the execution.
- 3Monitor and limit agent spendingAn operator can set caps on reported spending to prevent an agent from consuming excessive resources.
Written from the project's README. Every use case is checked against a quote from it.
DeadBolt MCP tools 2
Read from the server with tools/listdeadbolt_get_integration_guideRead-onlyGet local, read-only DeadBolt setup steps for a supported integration route. Returns operator responsibilities, a placeholder configuration and the enforcement boundary. Does not create files, run a server or grant permission. Available only when operator configuration is blank.
deadbolt_check_bundleRead-onlyRead the bundled engine and provenance metadata, calculate its SHA-256 and report compatibility and packaging integrity for this host. Reads only this installed bundle; does not execute the engine, inspect operator state or test security. Available only when operator configuration is blank.
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableseanebones-lang/deadbolt is public and reachablegithub.com/seanebones-lang/deadbolt ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-12github.com/seanebones-lang/deadbolt ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubDeadBolt
Contributing with an agent? Read AGENTS.md for setup, local checks and project boundaries.
A local execution gate for software agents. Put DeadBolt in the code that runs an action, then let policy and operator controls decide whether that action runs. Embed it in Rust, call its local sidecar from another language, or wrap a trusted stdio MCP server. Free under Apache-2.0.
Install · Try it · Integrate · Migration · Project site
Recent evaluation evidence: ProtocolProbe's read-only setup inspection and NextEleven's separate Swarm native integration lab, with their tested scopes and remaining limits.
SQLite security update: engine 2.0.2
Download engine 2.0.2 to receive the fix for RUSTSEC-2026-0459. All four native targets are published; Mac downloads are signed and notarized. Source builds require Rust 1.89+. Existing 2.0.1 engines, plugin/bundle copies and previously built containers keep their original SQLite until replaced.
This source targets engine and Python client 2.0.2. The Python package contains no engine. Cargo/PyPI registries, Homebrew, MCP bundles and plugin copies are separate rollout steps; consult distribution status before selecting a route. A source merge does not upgrade installed copies.
Upgrading an existing install? Engine, Python client, editor plugins and running sidecars are separate copies. Installing one does not upgrade the others. Use the distribution status and upgrade checklist to identify your route, verify its actual version and select the matching download.
Version 2 requires authenticated operator setup for Unix and TCP sidecars, creates private state, defaults fresh roots to supervisor renewal, and enforces ancestor policy and fixed run deadlines. Existing stored renewal modes remain unchanged. Read major-version migration and private state before replacing an older installation.
The artifact-pinned RC3 retest passed conflicting-destination denial, damaged-store Cursor Reload refusal, and actual model calls after a fixed deadline on macOS arm64. The underlying Auto model was unknown. Separate Linux headless checks cover their recorded scope. These are execution receipts, not certification; stable artifact and installed-consumer checks remain distinct from the RC3 results.
Try it before connecting an agent
No model account, API key, Harness, cloud service or database server is needed. Choose a checksum-verified native archive in the installation guide. From its extracted directory on macOS/Linux:
chmod 0755 deadbolt
./deadbolt --version
./deadbolt drill
python3 examples/evaluate.py --binary ./deadbolt
On Windows, use .\deadbolt.exe --version, .\deadbolt.exe drill and
python examples/evaluate.py --binary .\deadbolt.exe.
Expected: your selected version, deadbolt drill ok, and JSON with "passed": true.
The evaluation starts a private sidecar, writes harmless temporary files, checks
that policy, approval, kill and outage block effects, and cleans up afterward.
Python 3.9+ is the additional runtime needed. Understand the report.
For a reviewed source checkout, Rust 1.89+ and a native C compiler/linker:
cargo install --path . --locked --bin deadbolt
deadbolt --version
deadbolt drill
The matching Python client 2.0.1.post1 is published. The matching Rust package 2.0.1 is also published. Install the CLI from Cargo, or the Python client in your application environment:
cargo install n11-deadbolt --version 2.0.1 --locked --bin deadbolt
# In your application's virtual environment:
python -m pip install 'n11-deadbolt-client==2.0.1.post1'
For embedded Rust, use deadbolt = { package = "n11-deadbolt", version = "=2.0.1" }
and commit your application's own lockfile. The Python wheel contains the client,
not the engine. Node remains a bundled source module. Install and verify.
Pick your integration
| Your executor | Smallest integration | Start here |
|---|---|---|
| Rust application | Embedded store and a check at actual dispatch | Rust |
| Python application | Local sidecar and dispatch around the actual function |
Python |
| OpenAI Agents SDK function tools | Sidecar and @protected_tool on each protected function |
SDK adapter |
| FastMCP server you own | Sidecar and dispatch_async inside protected tool bodies |
Offline recipe |
| Node or another language | Local sidecar; source Node client or HTTP protocol | Sidecar |
| Trusted stdio MCP server | deadbolt mcp-proxy … -- SERVER |
MCP |
| Desktop MCP client | Verified local bundle and private operator configuration | Bundle and editor routes |
| Docker-launched MCP client | Source-built stdio container and trusted downstream | Docker |
Choose the exact bundle and matching configuration before installation. Blank configuration exposes two read-only setup tools and provides no active protection. Configured tools come from your trusted downstream server. Version 2 bundle runs require a fixed deadline, deliberate renewal mode and reviewed offline exceptions. The bundle uses broad one-shot tool approvals; it does not provision exact-action grants. Configuration · Editor guide.
Download the current bundle from the explicit 2.0.1 release. The official MCP Registry now publishes 2.0.1 with the matching bundle checksum. Verify the entry's actual version and checksum before installing. Discovery is not hosted operator access, marketplace acceptance of another submission, or an endorsement.
Put the gate at the effect
Your trusted executor creates the run and configures policy first. With the matching Python client installed and its sidecar configured:
from pathlib import Path
from deadbolt_client import dispatch
outcome = dispatch(
"executor-run-001", "write_file",
lambda: Path("output.txt").write_text("allowed work"),
)
if not outcome["executed"]:
print("Action blocked:", outcome["decision"]["code"])
A fresh admission happens before the callback; a denial leaves the body uncalled.
Complete setup covers provisioning, policy, credentials,
transport and errors. Wrap every protected route. Never cache an allow or split
one-shot admission from execution. ensure confirms record presence, not liveness.
Controls and limits
- Tool and destination policies, reported-spend caps, pause, clips and operator kill.
- Default 60-second idle TTL. A separate supervisor maintains fresh runs; explicit activity mode is available. Neither mode can move a fixed deadline or revive expired/killed state. Liveness · Deadlines.
- Descendants obey ancestor restrictions. A child policy cannot widen its parent.
- Broad one-shot tool approvals and exact-action grants for trusted integrations using the content-bound API.
- Scoped admission credentials separate dispatch from
operator controls.
/spendremains operator-only. - SQLite evidence, JSONL mirrors and per-agent incident exports.
- Store or transport failure denies protected dispatch; malformed or unsuccessful responses never authorize the body.
Ordinary trusted-executor admission treats unset policy lists as open; the MCP proxy requires explicit tool policy. Configure runs and children before dispatch. MCP discovery can advertise tools that the policy will deny. Destination parsing covers recognized fields, not arbitrary arguments or network traffic. Destination policy.
Know the boundary
DeadBolt protects connected execution routes. It does not sandbox arbitrary code, stop a provider, or make external effects transactional with admission. Kill blocks subsequent admissions; stopping in-flight work requires an executor cancellation pattern. The MCP child remains trusted and has OS access; startup and non-tool methods are outside the tool-call gate.
Keep state and operator authority outside untrusted agent processes. A process able to write the database or invoke the operator CLI has operator authority; socket credentials cannot contain it. Use separate OS/service ownership and OS egress controls where your application requires those boundaries. Evidence hashes identify content; operator-writable records are not tamper-proof certification. Trust · HTTP authentication · Pilot checklist.
Developer documentation
| Need | Guide |
|---|---|
| First working result | Quick start, first evaluation |
| Binary, crate or Python installation | Installation |
| Embed, sidecar or MCP wiring | Integration, Python / SDK |
| Least-authority dispatch and sensitive actions | Credentials, exact approvals |
| API and upgrade behavior | HTTP protocol, compatibility |
| Denial or setup problem | Troubleshooting, FAQ |
| Deploy, backup and respond | Operations, incidents |
| Evaluate or contribute | Technical brief, Hermes showcase, contributing |
| Versions and packaging | Changelog, release procedure, third-party notices |
Source checks: cargo test --locked, cargo clippy --all-targets --locked -- -D warnings,
and python3 tests/client_contract.py after cargo build --locked --bin deadbolt
(Python and Node required). CI also checks Rust 1.89, installed Python/SDK behavior
and native packages. Passing these checks does not establish acceptance of your application.
Report ordinary bugs or use private security reporting. Copyright NextEleven LLC 2026. License · Notice. Harness is one consumer, not a prerequisite.
For trusted executors that need to stop already running local commands, the owned-process cancellation reference adds a POSIX supervisor pattern with disposable acceptance. It does not change the gate into a sandbox or add enforcement to older packages.
DeadBolt MCP questions
What tools does DeadBolt MCP provide?
It exposes 2 tools, including deadbolt_get_integration_guide, deadbolt_check_bundle.
Does DeadBolt sandbox arbitrary code?
No, DeadBolt protects connected execution routes but does not sandbox arbitrary code or make external effects transactional.
How can I integrate DeadBolt with an existing MCP server?
You can wrap a trusted stdio MCP server using the command deadbolt mcp-proxy … -- SERVER.
What happens if a tool call is denied?
A denial prevents the function body from being called, and the outcome will indicate the decision code.
Do I need a cloud service or API key to try it?
No, no model account, API key, Harness, cloud service or database server is needed to try it.