Blast Scope

Contextual blast-radius scoring for shell commands an AI agent is about to run

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

Add to Cursor Add to VS Code

Not yet automatically verified

We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag — we're steadily working through the catalog.

Manual Client & Custom JSON ConfigExpand JSON ▾

Client Config & Setup

Choose your client or environment

Target File:~/Library/Application Support/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "blast-scope": {
      "command": "uvx",
      "args": [
        "blast-scope"
      ]
    }
  }
}

💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.

Documentation Overview

Blast Scope

A consequence engine for shell commands. Blast Scope scores what a command would actually do — before an AI agent (or you) runs it. It doesn't pattern-match syntax into a blocklist; it figures out the command's real target, observes that target with a safe, read-only probe, and returns a structured risk score with evidence.

The whole point is contextual blast radius. The same command gets a completely different score depending on what it would actually hit:

Dockerfile

COMMAND                            SEVERITY   WHY                                          ADVICE
─────────────────────────────────  ────────   ──────────────────────────────────────────  ───────
rm -rf ./logs                      LOW        0 importers · regenerable · outside src      proceed
rm -rf ./config                    CRITICAL   8 modules import it · high PageRank hub      block
git reset --hard   (clean tree)    LOW        nothing uncommitted to discard               proceed
git reset --hard   (4 dirty files) HIGH       would throw away 4 files of uncommitted work confirm
git push --force   (protected)     CRITICAL   would orphan commits on a protected branch   block
docker volume rm cache  (absent)   LOW        volume doesn't exist — nothing to remove     proceed
docker volume rm pgdata (in use)   CRITICAL   holds data · in use · no image to rebuild    block
pip uninstall flask     (uv.lock)  LOW        regenerable — exact version pinned in lock   proceed
DROP TABLE users        (42 rows)  CRITICAL   schema + 42 rows · irreversible              block
DELETE FROM logs        (in txn)   HIGH       no WHERE — but inside a txn, ROLLBACK-able    confirm

Two commands can be byte-identical and score four bands apart. That gap is the product.

Not a blocklist. Not a replacement for Shellfirm. Not a syscall monitor. It scores structural consequence — advisory, never blocking — and for the rare critical command it captures an undo snapshot first.

How it works

A command flows through a cheap funnel: almost everything is recognized as non-destructive in microseconds and exits silent. Only a flagged destructive candidate pays for a probe.

Code

  shell command
      │   split chains (&& || ; |) · de-alias PowerShell · parse flags/targets
      ▼
  ┌──────────────────────────────────────────────────────────────────────┐
  │  STAGE 1 · triage  (near-free regex — runs on every command)          │
  │     which class?   git · docker · pip/uv · sql · else filesystem       │
  │     destructive?   `git status` → no.   `git reset --hard` → yes ↓     │
  └───────────────────────────────┬──────────────────────────────────────┘
                    destructive candidate │   (everything else exits here, silent)
                                          ▼
  ┌──────────────────────────────────────────────────────────────────────┐
  │  ELIGIBILITY FILTER   safe read-only probe?   AND   undo authorable?   │
  └──────────────┬──────────────────────────────────────┬─────────────────┘
         yes, probe it │                       no probe here / now │
                       ▼                                           ▼
   STAGE 2 · safe probe (read-only)                    heuristic estimate
     git  status · reflog · rev-list                   from a static per-class
     docker  inspect · ps · ls                          table — and LABELED
     sqlite  SELECT count(*)  [mode=ro]                  "(estimated)" so you
     pip/uv  read lockfiles                              know it wasn't probed
                       │                                           │
                       └─────────────────────┬─────────────────────┘
                                              ▼
        blast radius  ×  reversibility   (combined PER CLASS — no global formula)
        filesystem also folds in: dependency-graph centrality + recoverability
                                              ▼
              score 0.0–1.0  →  severity (low / medium / high / critical)
                                              ▼
        PreToolUse hook:  silent (low/med) · advise (high) · advise + snapshot (critical)

The eligibility filter is the design boundary. A command class earns a live probe only when both hold: (1) its impact is observable by a strictly side-effect-free read (HTTP-GET sense — never mutate state to assess state), and (2) its undo story is well-known enough to encode in a static table. When a probe can't run here and now (no docker daemon, no DB driver, no creds), the tool degrades to a labeled estimate — it never guesses silently, and it never blocks.

See docs/heuristics.md for the per-class tables, the exact filesystem formula, and calibration.

The five command classes

Class	Destructive ops it scores	Safe (read-only) probe	Reversibility signal
Filesystem	`rm -rf`, `mv`, `>` truncate	dependency graph + git status	git-tracked? regenerable? secret? precious?
Git	`reset --hard`, `push --force`, `branch -D`, `clean -fdx`	`status` · `reflog` · `rev-list` · `rev-parse @{u}`	reflog window · remote ahead · protected branch
Docker	`volume rm`, `system prune -a`, `rm -f`	`volume inspect` · `ps -a` · `volume ls`	volume → none · container → recreatable from image
pip / uv	`pip uninstall`, `uv pip uninstall`	read lockfile / manifest (no subprocess)	lockfile present → fully regenerable
SQL	`DROP`, `TRUNCATE`, `DELETE` without `WHERE`	SQLite: `SELECT count(*)` `mode=ro`; transaction check	inside a transaction? backup posture?

New classes drop in behind one protocol (triage / assess) in src/blast_scope/classes/; each class confines assess to strictly side-effect-free reads.

Status

Calibrated multi-class guardrail with command resolution and a precise dependency graph.

Capability	Module
Flag/operand-sensitive command model (POSIX and PowerShell)	`command_effects.py`, `command_parser.py`
Command resolution — env/tilde/brace/glob expansion, unset-var hazards, script transparency (`sh -c`, `npm run` + pre/post hooks, script files, Makefile targets), read-only `$(...)` substitution	`resolution.py`
Dry-run oracles — `git clean -n` exact lists, reset divergence, checkout clobber preview, `find -delete`→`-print` rewrite, sqlite scoped-DELETE counts, rsync `--dry-run`; oracle targets feed the undo snapshot	`classes/git.py`, `classes/find.py`, `classes/rsync.py`, `classes/sql.py`
Recoverability classification (git state, secrets, regenerable, precious data)	`recoverability.py`
Dependency graph + weighted PageRank centrality, incremental indexing	`graph_resolver.py`, `centrality.py`
Two-axis, evidence-based filesystem scoring	`risk_scorer.py`
Command-class probes — git / docker / pip·uv / SQL, behind one protocol	`classes/`
Out-of-graph path analyzers (infra / config-by-path) + git base	`consequences.py`, `vcs.py`, `infra.py`, `config_refs.py`
PreToolUse hook + tarball snapshot/undo	`hook.py`, `snapshot.py`
Eval harness + labeled corpus + calibration	`eval.py`, `tests/fixtures/eval_corpus.jsonl`

Calibration. Two harnesses, both run-it-yourself:

In-repo corpus (tests/fixtures/eval_corpus.jsonl, 58 cases spanning every recoverability category, git working-tree state, infra/config, rm -rf .git, a graph-indexed central module, the git/docker/pip/SQL classes, and the resolution layer — unset-var collapses, glob/env-var targets, sh -c payloads, npm pre-hooks, opaque wrappers, mass destruction of tracked source) — 58/58 exact severity, gate F1 1.00, pinned by tests/test_eval.py with headroom so changes can't silently regress.
SABER — 716 real coding-agent workspaces. Against ~1725 safe commands, blast-scope's false-positive rate is 0.58%; on its core competency (data_destruction) it catches 82.4% of injected attacks on realistic workspaces — on the fast hook path, no graph required, thanks to command resolution (env/glob binding + script transparency). Wrapper transparency also lifts code_tampering from ~0% to 50%. The per-category recall is deliberately uneven, and the table says so: blast-scope scores destructive consequence — filesystem/data loss plus git/docker/pip/SQL state. Network exfiltration and persistence are a different threat model, out of scope by design — not an unfinished corner. That's the boundary, drawn on purpose. See bench/.

bash

uv run python -m blast_scope.eval                 # in-repo corpus
python bench/saber_eval.py --tasks <saber>/dataset/data/tasks.jsonl   # SABER

Installation

The fastest path for any MCP client is zero-install via uvx (no clone, no venv):

bash

uvx blast-scope        # runs the MCP server on stdio

Claude Code users — one line wires up both the MCP tools and the advisory hook:

bash

/plugin marketplace add Atharva-Jayappa/blast-scope
/plugin install blast-scope

For development, or to pin a checkout:

bash

git clone https://github.com/Atharva-Jayappa/blast-scope.git
cd blast-scope && uv sync --all-extras

Usage

As an MCP server

Add to your MCP client config (e.g. Claude Code settings.json):

config.json

{
  "mcpServers": {
    "blast-scope": { "command": "uvx", "args": ["blast-scope"], "type": "stdio" }
  }
}

Tools exposed:

Read the full README →View source on GitHub →

Related MCP Servers

View all in Biology & Bioinformatics View all alternatives

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

Last commit

1mo ago

Most recent push to the default branch.

Directory activity

1 views

Config copies, upvotes, and views on AllMCPs.

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about Blast Scope

Add the following block to your claude_desktop_config.json under mcpServers: "mcpServers": { "blast-scope": { "command": "uvx", "args": ["blast-scope"] } }

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:

Live Dynamic SVG Preview

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/blast-scope?style=directory)](https://allmcps.com/mcp/blast-scope)

HTML Embed

<a href="https://allmcps.com/mcp/blast-scope"><img src="https://allmcps.com/api/badge/blast-scope?style=directory" alt="Blast Scope on AllMCPs" /></a>

Technical Specs & Signals

CategoryBiology & Bioinformatics

2/7 checks healthy over the last 45d

36Quality signal: Fair · 36/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership10/20

Documentation & tools15/30

Adoption & activity2/15

Community engagement0/10

A guidance signal from public completeness & health data — not a user rating. New listings start lower and rise as they add docs, get verified, and grow adoption. Signals we can't observe for a listing are skipped, not counted against it.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 5d ago via OSV.dev · blast-scope (PyPI)

★ Featured

Moxie Docs MCP

MCP & Agent Skills for Automated Documentation, and codebase conventions + context

Explore Server →

Own this project?

This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to unlock edit access and the Official badge and attach your website — proof is checked automatically, then reviewed by our team.

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 🧬 Biology & Bioinformatics →Alternatives to Blast Scope →Install in Claude Desktop Install in Cursor Install in VS Code Setup guides for all 13 MCP clients

Blast Scope

Contextual blast-radius scoring for shell commands an AI agent is about to run

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

Add to Cursor Add to VS Code

Not yet automatically verified

We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag — we're steadily working through the catalog.

Manual Client & Custom JSON ConfigExpand JSON ▾

Client Config & Setup

Choose your client or environment

Target File:~/Library/Application Support/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "blast-scope": {
      "command": "uvx",
      "args": [
        "blast-scope"
      ]
    }
  }
}

💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.

Documentation Overview

Blast Scope

The whole point is contextual blast radius. The same command gets a completely different score depending on what it would actually hit:

Dockerfile

COMMAND                            SEVERITY   WHY                                          ADVICE
─────────────────────────────────  ────────   ──────────────────────────────────────────  ───────
rm -rf ./logs                      LOW        0 importers · regenerable · outside src      proceed
rm -rf ./config                    CRITICAL   8 modules import it · high PageRank hub      block
git reset --hard   (clean tree)    LOW        nothing uncommitted to discard               proceed
git reset --hard   (4 dirty files) HIGH       would throw away 4 files of uncommitted work confirm
git push --force   (protected)     CRITICAL   would orphan commits on a protected branch   block
docker volume rm cache  (absent)   LOW        volume doesn't exist — nothing to remove     proceed
docker volume rm pgdata (in use)   CRITICAL   holds data · in use · no image to rebuild    block
pip uninstall flask     (uv.lock)  LOW        regenerable — exact version pinned in lock   proceed
DROP TABLE users        (42 rows)  CRITICAL   schema + 42 rows · irreversible              block
DELETE FROM logs        (in txn)   HIGH       no WHERE — but inside a txn, ROLLBACK-able    confirm

Two commands can be byte-identical and score four bands apart. That gap is the product.

Not a blocklist. Not a replacement for Shellfirm. Not a syscall monitor. It scores structural consequence — advisory, never blocking — and for the rare critical command it captures an undo snapshot first.

How it works

A command flows through a cheap funnel: almost everything is recognized as non-destructive in microseconds and exits silent. Only a flagged destructive candidate pays for a probe.

Code

  shell command
      │   split chains (&& || ; |) · de-alias PowerShell · parse flags/targets
      ▼
  ┌──────────────────────────────────────────────────────────────────────┐
  │  STAGE 1 · triage  (near-free regex — runs on every command)          │
  │     which class?   git · docker · pip/uv · sql · else filesystem       │
  │     destructive?   `git status` → no.   `git reset --hard` → yes ↓     │
  └───────────────────────────────┬──────────────────────────────────────┘
                    destructive candidate │   (everything else exits here, silent)
                                          ▼
  ┌──────────────────────────────────────────────────────────────────────┐
  │  ELIGIBILITY FILTER   safe read-only probe?   AND   undo authorable?   │
  └──────────────┬──────────────────────────────────────┬─────────────────┘
         yes, probe it │                       no probe here / now │
                       ▼                                           ▼
   STAGE 2 · safe probe (read-only)                    heuristic estimate
     git  status · reflog · rev-list                   from a static per-class
     docker  inspect · ps · ls                          table — and LABELED
     sqlite  SELECT count(*)  [mode=ro]                  "(estimated)" so you
     pip/uv  read lockfiles                              know it wasn't probed
                       │                                           │
                       └─────────────────────┬─────────────────────┘
                                              ▼
        blast radius  ×  reversibility   (combined PER CLASS — no global formula)
        filesystem also folds in: dependency-graph centrality + recoverability
                                              ▼
              score 0.0–1.0  →  severity (low / medium / high / critical)
                                              ▼
        PreToolUse hook:  silent (low/med) · advise (high) · advise + snapshot (critical)

See docs/heuristics.md for the per-class tables, the exact filesystem formula, and calibration.

The five command classes

Class	Destructive ops it scores	Safe (read-only) probe	Reversibility signal
Filesystem	`rm -rf`, `mv`, `>` truncate	dependency graph + git status	git-tracked? regenerable? secret? precious?
Git	`reset --hard`, `push --force`, `branch -D`, `clean -fdx`	`status` · `reflog` · `rev-list` · `rev-parse @{u}`	reflog window · remote ahead · protected branch
Docker	`volume rm`, `system prune -a`, `rm -f`	`volume inspect` · `ps -a` · `volume ls`	volume → none · container → recreatable from image
pip / uv	`pip uninstall`, `uv pip uninstall`	read lockfile / manifest (no subprocess)	lockfile present → fully regenerable
SQL	`DROP`, `TRUNCATE`, `DELETE` without `WHERE`	SQLite: `SELECT count(*)` `mode=ro`; transaction check	inside a transaction? backup posture?

New classes drop in behind one protocol (triage / assess) in src/blast_scope/classes/; each class confines assess to strictly side-effect-free reads.

Status

Calibrated multi-class guardrail with command resolution and a precise dependency graph.

Capability	Module
Flag/operand-sensitive command model (POSIX and PowerShell)	`command_effects.py`, `command_parser.py`
Command resolution — env/tilde/brace/glob expansion, unset-var hazards, script transparency (`sh -c`, `npm run` + pre/post hooks, script files, Makefile targets), read-only `$(...)` substitution	`resolution.py`
Dry-run oracles — `git clean -n` exact lists, reset divergence, checkout clobber preview, `find -delete`→`-print` rewrite, sqlite scoped-DELETE counts, rsync `--dry-run`; oracle targets feed the undo snapshot	`classes/git.py`, `classes/find.py`, `classes/rsync.py`, `classes/sql.py`
Recoverability classification (git state, secrets, regenerable, precious data)	`recoverability.py`
Dependency graph + weighted PageRank centrality, incremental indexing	`graph_resolver.py`, `centrality.py`
Two-axis, evidence-based filesystem scoring	`risk_scorer.py`
Command-class probes — git / docker / pip·uv / SQL, behind one protocol	`classes/`
Out-of-graph path analyzers (infra / config-by-path) + git base	`consequences.py`, `vcs.py`, `infra.py`, `config_refs.py`
PreToolUse hook + tarball snapshot/undo	`hook.py`, `snapshot.py`
Eval harness + labeled corpus + calibration	`eval.py`, `tests/fixtures/eval_corpus.jsonl`

Calibration. Two harnesses, both run-it-yourself:

In-repo corpus (tests/fixtures/eval_corpus.jsonl, 58 cases spanning every recoverability category, git working-tree state, infra/config, rm -rf .git, a graph-indexed central module, the git/docker/pip/SQL classes, and the resolution layer — unset-var collapses, glob/env-var targets, sh -c payloads, npm pre-hooks, opaque wrappers, mass destruction of tracked source) — 58/58 exact severity, gate F1 1.00, pinned by tests/test_eval.py with headroom so changes can't silently regress.
SABER — 716 real coding-agent workspaces. Against ~1725 safe commands, blast-scope's false-positive rate is 0.58%; on its core competency (data_destruction) it catches 82.4% of injected attacks on realistic workspaces — on the fast hook path, no graph required, thanks to command resolution (env/glob binding + script transparency). Wrapper transparency also lifts code_tampering from ~0% to 50%. The per-category recall is deliberately uneven, and the table says so: blast-scope scores destructive consequence — filesystem/data loss plus git/docker/pip/SQL state. Network exfiltration and persistence are a different threat model, out of scope by design — not an unfinished corner. That's the boundary, drawn on purpose. See bench/.

bash

uv run python -m blast_scope.eval                 # in-repo corpus
python bench/saber_eval.py --tasks <saber>/dataset/data/tasks.jsonl   # SABER

Installation

The fastest path for any MCP client is zero-install via uvx (no clone, no venv):

bash

uvx blast-scope        # runs the MCP server on stdio

Claude Code users — one line wires up both the MCP tools and the advisory hook:

bash

/plugin marketplace add Atharva-Jayappa/blast-scope
/plugin install blast-scope

For development, or to pin a checkout:

bash

git clone https://github.com/Atharva-Jayappa/blast-scope.git
cd blast-scope && uv sync --all-extras

Usage

As an MCP server

Add to your MCP client config (e.g. Claude Code settings.json):

config.json

{
  "mcpServers": {
    "blast-scope": { "command": "uvx", "args": ["blast-scope"], "type": "stdio" }
  }
}

Tools exposed:

Read the full README →View source on GitHub →

Related MCP Servers

View all in Biology & Bioinformatics View all alternatives

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

Last commit

1mo ago

Most recent push to the default branch.

Directory activity

1 views

Config copies, upvotes, and views on AllMCPs.

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about Blast Scope

Add the following block to your claude_desktop_config.json under mcpServers: "mcpServers": { "blast-scope": { "command": "uvx", "args": ["blast-scope"] } }

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:

Live Dynamic SVG Preview

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/blast-scope?style=directory)](https://allmcps.com/mcp/blast-scope)

HTML Embed

<a href="https://allmcps.com/mcp/blast-scope"><img src="https://allmcps.com/api/badge/blast-scope?style=directory" alt="Blast Scope on AllMCPs" /></a>

Technical Specs & Signals

CategoryBiology & Bioinformatics

2/7 checks healthy over the last 45d

36Quality signal: Fair · 36/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership10/20

Documentation & tools15/30

Adoption & activity2/15

Community engagement0/10

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 5d ago via OSV.dev · blast-scope (PyPI)

★ Featured

Moxie Docs MCP

MCP & Agent Skills for Automated Documentation, and codebase conventions + context

Explore Server →

Own this project?

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 🧬 Biology & Bioinformatics →Alternatives to Blast Scope →Install in Claude Desktop Install in Cursor Install in VS Code Setup guides for all 13 MCP clients