blastcheck-mcp
Assesses Terraform plan files with blastcheck, producing an Impact Manifest that summarizes change safety, per-change findings, and preconditions in natural language.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@blastcheck-mcp Run blastcheck on plan.json and explain what could go wrong."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
blastcheck-mcp
An MCP server that gives coding agents (Claude Code, Claude Desktop, Cursor, and any other MCP client) the ability to assess Terraform plans with blastcheck: produce an Impact Manifest - a machine-readable change-safety assertion - and explain it in plain language.
Read-only and propose-only. No tool applies Terraform, mutates a cloud resource, or accepts a credential. This release performs no network I/O at all: everything runs offline against the plan file.
Quickstart
Requires Python 3.10+ and uv. No install step; the first run resolves everything:
uvx blastcheck-mcpClaude Code
claude mcp add blastcheck -- uvx blastcheck-mcpClaude Desktop
Add to claude_desktop_config.json (Settings > Developer > Edit
Config):
{
"mcpServers": {
"blastcheck": {
"command": "uvx",
"args": ["blastcheck-mcp"]
}
}
}Cursor
Add to ~/.cursor/mcp.json (or .cursor/mcp.json in a project):
{
"mcpServers": {
"blastcheck": {
"command": "uvx",
"args": ["blastcheck-mcp"]
}
}
}Related MCP server: iac-copilot
Using it
Ask your agent to check a plan:
terraform plan -out plan.tfplan
terraform show -json plan.tfplan > plan.jsonThen: "run blastcheck on plan.json and explain what could go wrong." The agent will call impact_emit, get a manifest handle plus a verdict summary, and follow up with impact_explain for the full picture. (impact_emit also accepts the saved .tfplan directly and converts it.)
Tools
impact_emit
Runs blastcheck's plan-only analysis on a terraform show -json file
(or a saved .tfplan) and returns:
manifest_handle- a short reference to the full Impact Manifest, written to a private temp file (0600, per-user 0700 directory, kept at most 24h). Pass it to impact_explain instead of shuttling the large document through model context.summary- the verdict, per-severity counts, which changes drove it, and the plan-only note.
A plan-only run can never emit safe - it never verified live state,
and blastcheck says so rather than guessing. That is the point of the
format.
impact_explain
Turns a manifest into markdown a human can act on: the verdict and why, each change's noteworthy findings with their rationales, a "safe if ..." checklist of unmet preconditions, and exactly what could not be verified. Deterministic local code; accepts a manifest_handle, a manifest_path, or the manifest inline (exactly one).
Output is capped by a hard budget (BLASTCHECK_MCP_EXPLAIN_BUDGET env, default 32000 characters, about 8K tokens) so the tool can never consume a session's context in one call. Small plans render in full. Large plans get a compact view: dimensions identical across every change are stated once, changes with identical assessments are grouped with numeric indexes compressed to ranges (app[0..11]) - for_each string keys are never wildcarded, so which tenants or keys are affected stays visible - and blocking changes always keep their complete address list, dropping only per-change repetition. Whenever anything is grouped or cut, an explicit partial-view notice says so and shows the exact follow-up calls; all lists are lexically sorted before any cut, so the same plan always shows the same subset. Never a silent drop.
Drill-down filters (optional, combined with AND):
severity- e.g.["blocking"]or["blocking", "caution"]module_prefix- address prefix, e.g."module.tenants[\"contoso-prod\"]"resource_type- exact type, e.g."azurerm_managed_disk"addresses- exact addresses, always rendered in full detail; the guaranteed path to any specific change
Compatibility
Verified against real clients and across MCP protocol eras (v0.1.0-rc1, mcp SDK 2.x, macOS, Python 3.13):
Check | Result |
Protocol 2024-11-05 (oldest era) | negotiated, tools list + calls work |
Protocol 2025-03-26 | negotiated, tools list + calls work |
Protocol 2025-06-18 | negotiated, tools list + calls work |
Unknown version offered | server answers with its latest, per spec |
Claude Code 2.0.76 (stdio) | connects; both tools exercised end to end in four separate headless runs (see cold-install row for the published-package run). Investigated note: when driving headless |
Cold install (uvx from PyPI, v0.1.0) | verified on a clean shell outside the repo with no local venv: |
Interactive session | the standing registration for interactive use points at the published |
Claude Desktop | config block above is the documented uvx form; not yet exercised on this machine |
Cursor | config block above is the documented uvx form; not yet exercised (Cursor not installed on the test machine) |
Large-plan compression | verified against a synthetic 288-change fixture ONLY (nested modules, for_each string keys, count indexes; 372KB full render compressed to a 12.5KB overview). NOT yet verified against a large real-world plan - if real changes fingerprint less uniformly, overviews will be larger; the hard output budget still caps them and the partial-view notice still applies. |
Errors
Failures come back as CODE: one clear sentence - for example
FILE_NOT_FOUND: no such file: plan.json or
MANIFEST_UNSUPPORTED_VERSION: ... - never a stack trace.
Data boundary
This release sends nothing anywhere: no telemetry, no API calls, no network I/O. Raw plan JSON never leaves the machine.
A future release adds an optional CloudRift tier (live cost, dependency
and tenant enrichment; see docs/remote-tier.md). Its boundary is
already implemented and tested in this codebase, before any network
code exists: if a manifest is ever scored remotely, what leaves the
machine is an identity-only projection - per change: address, resource
type, name, Terraform provider address, and actions; plus the
manifest's schema_version, generated_at, producer name/version, and
source type. Evidence, rationales, verdicts, attribute values (ports,
CIDRs, sizes), and the plan itself are stripped by an explicit
allowlist, so a future manifest field is excluded by default rather
than leaked by default. That tier will require an explicit
CLOUDRIFT_API_TOKEN; without one, the server registers the local tools
only.
Environment variables
Variable | Effect |
BLASTCHECK_MCP_EXPLAIN_BUDGET | Hard cap, in characters, on impact_explain output (default 32000, floor 4000). Over the cap, a compact grouped view with an explicit partial-view notice is returned instead - never a silent cut. |
CLOUDRIFT_API_TOKEN | Reserved for the future remote tier. If set today, the server notes on stderr that the remote tier is not in this release and runs the local tools only. Credentials are NEVER accepted as tool arguments. |
Development
python3 -m venv .venv
.venv/bin/pip install -e ".[test]"
.venv/bin/pytestThe suite is fully offline. tests/test_project.py holds the
data-boundary tests; treat a failure there as a stop-ship.
Relationship to blastcheck and the spec
blastcheck-mcp is a thin MCP layer over the
blastcheck library
(pinned >=0.7,<0.8) and implements a consumer of the
Impact Manifest specification
(schema major version 0). The manifest schema is read from blastcheck's
own vendored copy, so there is no second copy to drift.
License
Apache-2.0. See LICENSE.
Available Tools
2 toolsimpact_emitARead-only
Produce an Impact Manifest (a machine-readable change-safety assertion) from a Terraform plan, using blastcheck.
plan_path may point at terraform show -json output or at a saved
.tfplan file (converted automatically). The analysis is offline and
plan-only: nothing is sent anywhere, no cloud credentials are used,
and a plan-only manifest can never claim safe - it says what it
verified and what it could not.
Returns a manifest_handle (pass it to impact_explain) plus a short summary. The full manifest is written to a private temp file rather than returned inline, because it is large.
Inputs: plan_path (required). Returns: result
impact_explainARead-only
Explain an Impact Manifest in plain language.
Provide exactly one of: manifest_handle (from impact_emit), manifest_path (a manifest JSON file on disk), or manifest (the document inline). Returns markdown covering the verdict and why, each change's noteworthy findings, a "safe if ..." checklist of unmet preconditions, and what could not be verified.
Output is capped by a hard budget (BLASTCHECK_MCP_EXPLAIN_BUDGET env, default 32000 characters). Large plans get a compact grouped view with an explicit partial-view notice - never a silent cut. Drill down with the optional filters, which combine with AND: severity (e.g. ["blocking"]), module_prefix (address prefix), resource_type (exact, e.g. "azurerm_managed_disk"), and addresses (exact addresses, always rendered in full detail - the guaranteed path to any specific change). All lists are lexically sorted before any cut, so the same plan always shows the same subset.
Purely local and deterministic; nothing is sent anywhere.
Inputs: manifest, severity, addresses, manifest_path, +3 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct roles: impact_emit produces a manifest from a Terraform plan, while impact_explain consumes an existing manifest and explains it. There is no overlap or possible misselection between them.
Both tools follow the same predictable prefix-plus-verb pattern: impact_emit and impact_explain. The naming is consistent and immediately signals the shared domain and the action each tool performs.
Two tools is on the thin side by the general rubric, but the server has a very narrow purpose: emit and explain impact manifests. The pair is reasonable for that scope, though it barely crosses the 'feels thin' boundary.
For the stated domain, the lifecycle is complete: impact_emit generates a manifest from a plan, and impact_explain supports all reasonable input paths (handle, file, or inline) and offers filtering for drill-down. There are no obvious missing operations for this focused workflow.
Maintenance
Related MCP Connectors
Security reviews for coding agents: diffs checked against your org policy and live infrastructure.
Code intelligence platform for AI agents. 20 tools for architecture, security & impact analysis.
IaC, CI and dependency security review for coding agents: local scan CLI plus hosted OAuth MCP.
Plan Salesforce deploys, open pull requests and trigger pipelines from your AI client.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI coding agents to plan, policy-check, and cost-estimate Terraform changes while requiring human approval through Slack or CLI before any terraform apply can execute.97 npmMIT
- AlicenseAqualityCmaintenanceEnables AI coding agents to search a security corpus, scan Terraform plan JSON for cited findings, and list sources via MCP tools grounded in CIS AWS Foundations and OWASP Top 10 CI/CD risks.3Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables state-aware Terraform/OpenTofu plan evaluation against live AWS topology and CloudWatch telemetry, detecting reliability blast radius and FinOps waste before merge.Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables coding agents to check npm packages, GitHub Action refs, and remote scripts before execution, returning deterministic ALLOW/DENY/REVIEW verdicts with evidence and a re-checkable manifest.MIT