# STATICA STATIC analysis tools (mcpb · statica-mcp.mcpb)

Drive Suresoft STATIC analysis from a coding agent: connect, analyze, upload, manage rulesets.

- Trust score: 47/100 (low)
- Change this week: +5
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- mcpb · `statica-mcp.mcpb`: 47/100 (this document), [markdown](https://verifymcp.io/servers/suresofttechnologies-statica-mcp/statica-mcp.md), [page](https://verifymcp.io/servers/suresofttechnologies-statica-mcp/statica-mcp)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/SuresoftTechnologies/statica-plugin/releases/download/v0.1.0/statica-mcp.mcpb`
- Transport: `stdio`
- SHA-256: `503b8ac4e50933c9c393c178e10ae83ea8c08008a2c7008e064bae35e902515a`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 11 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 82/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3154 tokens (~131/item across 24 items; 24 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 24 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 25 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the STATICA STATIC analysis tools MCP server?

STATICA STATIC analysis tools ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, 503b8ac4e50933c9c393c178e10ae83ea8c08008a2c7008e064bae35e902515a; the commands to do that are on this page. If it does not match, do not open it.

- Download bundle: `https://github.com/SuresoftTechnologies/statica-plugin/releases/download/v0.1.0/statica-mcp.mcpb`
- SHA-256: `503b8ac4e50933c9c393c178e10ae83ea8c08008a2c7008e064bae35e902515a`

### Verify on macOS / Linux

```bash
echo "503b8ac4e50933c9c393c178e10ae83ea8c08008a2c7008e064bae35e902515a  statica-mcp.mcpb" | shasum -a 256 -c
```

### Verify on Windows (PowerShell)

```powershell
(Get-FileHash -Algorithm SHA256 .\statica-mcp.mcpb).Hash -eq "503b8ac4e50933c9c393c178e10ae83ea8c08008a2c7008e064bae35e902515a"
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 47, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 46, +4)

- [functional improvement] Stability: unverified → 0.30

### 2026-11-12 (score 42, +1)

- [functional improvement] Maintenance: unverified → pass

### 2026-11-11 (score 41, 0)

- [security regression] Provenance: unverified → fail
- [functional regression] Security disclosure: unverified → fail

### 2026-11-10 (score 41)

First indexed and scored.

## MCP tools (24)

### `statica_doctor` (~55 tokens)

Check STATIC environment

Check that the local STATIC installation, analyzers, server URL and AccessKey are usable, and report which Python this MCP server runs on. Needs no project. Run this first when other STATICA tools fail with setup errors.

### `statica_status` (~131 tokens)

Show project STATIC status

Show how this project relates to STATIC in one call: link state, bootstrap status, automatic-analysis switch (per project and global), scope exclusions, and the server's ruleset, metric, report-generator and last-analysis state. Changes nothing. project.linked=false is a valid answer (not connected), not a failure. Server sections carry their own 'error'; one failing does not invalidate the rest.

Input parameters:

- `local` (boolean): Skip the server queries and report local state only (faster).
- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).

### `statica_pre_analyze` (~226 tokens)

Analyze changed files

Run STATIC on the files that changed since the last analysis and summarize defects by rule. Never uploads. For C/C++ only changed translation units run; Java, Kotlin, Python and C# are analyzed in full and the summary is narrowed to changed files. Counts cover this run's scope, not the project total - say so when reporting, and do not list defects file by file. reason=NO_CHANGES usually means the Stop hook already analyzed the edit; do not suggest a rebuild or upload for it. code=NEEDS_BOOTSTRAP means the project is not connected: offer to connect it (statica_get_guide topic=bootstrap) and start only after the user agrees. reason=BOOTSTRAP_IN_PROGRESS means a connection was started earlier: resume it per the guide, never start over.

Input parameters:

- `force` (boolean): Re-analyze even when nothing changed.
- `parallel` (integer): Analyzer parallelism. Omit for the default.
- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).

### `statica_set_auto_analysis` (~99 tokens)

Turn automatic analysis on or off

Turn the Stop-hook analysis after each response on or off, for this project or globally. Commands such as statica_pre_analyze keep working either way. Local setting only.

Input parameters:

- `enabled` (boolean, required): true to turn automatic analysis on, false to turn it off.
- `global` (boolean): Apply to every project instead of this one.
- `projectDir` (string): Absolute path of the project. Required unless global is true.

### `statica_scope_show` (~76 tokens)

Show analysis scope

List the files and directories excluded from analysis, the exceptions re-included inside excluded directories, and (C/C++ only) the build modules with their skip state. Changes nothing. Read this before changing the scope.

Input parameters:

- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).

### `statica_scope_exclude` (~141 tokens)

Exclude paths from analysis

Exclude files or directories from analysis. Adds to the current list. Real paths only (no globs); if any path is missing nothing is written (NO_SUCH_PATH). Headers cannot be excluded (NOT_ANALYZABLE). Defects already on the server stay until the next full analysis; when reporting later counts, say they changed because the scope changed, not the code. Confirm the exact paths with the user first.

Input parameters:

- `paths` (array, required): Paths relative to the project or absolute. File or directory is detected from disk.
- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).

### `statica_scope_include` (~78 tokens)

Re-include paths in analysis

Return files or directories to analysis, or re-include an exception inside an excluded directory. Real paths only; if any path is missing nothing is written.

Input parameters:

- `paths` (array, required): Paths relative to the project or absolute.
- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).

### `statica_scope_skip_module` (~100 tokens)

Skip C/C++ build modules

C/C++ only: skip whole build modules. Pass modules[].output from statica_scope_show. Unknown values are rejected (NO_SUCH_MODULE) with knownModules listed. Which modules are noise is the user's call; show the list and confirm first.

Input parameters:

- `paths` (array, required): Module build-output paths (modules[].output).
- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).

### `statica_scope_unskip_module` (~62 tokens)

Un-skip C/C++ build modules

C/C++ only: return skipped build modules to analysis.

Input parameters:

- `paths` (array, required): Module build-output paths (modules[].output).
- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).

### `statica_ruleset_show` (~51 tokens)

Show project rulesets

Show which rulesets the server project enables and the rule display language. Changes nothing.

Input parameters:

- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).

### `statica_ruleset_set` (~145 tokens)

Replace project rulesets

Replace the server project's ruleset selection. FULL REPLACEMENT: every ruleset not listed is turned off, so call statica_ruleset_show first and build on its current selection. At least one id is required. Applies to everyone using the server project; confirm the final list with the user before calling.

Input parameters:

- `localeLanguage` (string): Rule display language such as ko_KR or en_US. Omit to keep the current one.
- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).
- `rulesetIds` (array, required): Ids of every ruleset that should be on after the call.

### `statica_metric_show` (~45 tokens)

Show code metrics

Show which code metrics the server project enables. Changes nothing.

Input parameters:

- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).

### `statica_metric_set` (~94 tokens)

Turn code metrics on or off

Turn individual code metrics on or off by key (for example FUCYC). Metrics not named keep their state. Applies to everyone using the server project; confirm with the user first.

Input parameters:

- `off` (array): Metric keys to turn off.
- `on` (array): Metric keys to turn on.
- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).

### `statica_report_generator_show` (~55 tokens)

Show automatic report settings

Show whether the server generates a report after each analysis, and in which format and kinds. Changes nothing.

Input parameters:

- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).

### `statica_report_generator_set` (~115 tokens)

Set automatic report generation

Turn automatic report generation after each analysis on or off. Turning it on needs a format and at least one kind (1-12). Applies to everyone using the server project; confirm with the user first.

Input parameters:

- `enabled` (boolean, required): true to turn it on, false to turn it off.
- `format` (string): Report format.
- `kinds` (array): Report kinds 1-12.
- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).

### `statica_report` (~205 tokens)

Generate and download a report

Ask the server to generate a report from the latest revision, wait for it, and download it (default <project>/.static/reports/). Can take minutes. Kinds: 1 project summary, 2 remaining defects, 3 suppressed defects, 4 by rule, 5 by ruleset, 6 by severity, 7 by file, 8 module metrics, 9 file metrics, 10 class metrics, 11 function metrics, 12 suppressed metrics. On failure 'stage' tells how far it got.

Input parameters:

- `format` (string, required): Report format.
- `kinds` (array, required): Report kinds 1-12.
- `out` (string): Where to save the file. An existing file there is replaced. Omit for the default location.
- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).
- `timeout` (integer): Seconds to wait for generation (default 600).

### `statica_upload` (~149 tokens)

Analyze and upload to the server

Analyze the whole project and upload the result to the STATIC server as a new revision the whole team sees. Holds a licence slot and takes time. Call ONLY when the user explicitly asks to upload or publish results to the server; never as a follow-up to pre-analyze, a scope change or NO_CHANGES. returncode 113: the project is already being analyzed; 114: licence limit reached - ask the user to retry later. If ok is false, do not say the upload happened.

Input parameters:

- `parallel` (integer): Analyzer parallelism. Omit for the default.
- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).

### `statica_bootstrap_detect` (~115 tokens)

Gather bootstrap evidence

Step 1 of connecting a project to STATIC: collect build-system clues (artifacts: C/C++; languageArtifacts: Java, Kotlin, Python, C#) and the existing toolchain detector's view. Changes nothing. Choosing the language, environment and compiler from it is your judgement; follow statica_get_guide topic=bootstrap, and ask the user when clues point to more than one environment.

Input parameters:

- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).

### `statica_bootstrap_begin` (~385 tokens)

Create STATIC workspace and wrapper

Start connecting a project: verify the compiler by running it, then create the STATIC workspace and (C/C++) the compiler wrapper whose wrapperDir the build must be pointed at. Java and Kotlin also create the server project here. Does not edit project files. BEFORE CALLING: read statica_get_guide topic=bootstrap and get the user's approval for the whole connection - it later edits project build settings, runs a full build and creates a project on the shared server. C/C++ needs ide, compiler and compilerPath; other languages pass language and none of those. stage=existing-workspace means a workspace already exists: resume it (bootstrapping) or stop (ready), never start a second one.

Input parameters:

- `buildCommand` (string): Build command, if the build is not GUI-only. Omit rather than passing an empty string.
- `compiler` (string): C/C++ only: forge compiler value from the environments guide.
- `compilerPath` (string): C/C++ only: absolute path of the original compiler executable. Never guess it.
- `csharpConfiguration` (string): C# only: build configuration such as Debug or Release.
- `csharpTarget` (string): C# only: sdk for .NET 5+ / SDK-style projects, else framework (default).
- `ide` (string): C/C++ only: forge ide value from the environments guide.
- `input` (string): C# only: absolute path of the .sln or .csproj to analyze.
- `language` (string): Project language. Default ccpp (C/C++).
- `name` (string, required): Workspace name; becomes the server project key. Alphanumerics, at least 3 after dropping leading digits.
- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).

### `statica_bootstrap_guard` (~137 tokens)

Back up project files before editing

C/C++ only, and only when the substitution edits project files (guide type B: a hard-coded Makefile, Vitis CMakeLists.txt): keep the originals so statica_bootstrap_abort can restore them. Call right before editing. Do NOT call for command-line (A) or IDE/GUI (C) substitution, and never invent a file to satisfy the argument: a guarded file that did not exist is deleted on abort.

Input parameters:

- `files` (array, required): Existing project files about to be edited.
- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).

### `statica_bootstrap_verify` (~120 tokens)

Check the build was captured

After substituting the compiler and building (C/C++), or preparing the build descriptor (Java/Kotlin), check that STATIC has something to analyze. A successful build is not proof it went through the wrapper; ok=false means it did not. What to do next depends on the substitution type - see the guide (do not abort a GUI substitution). Also returns the workspace when resuming. Can be called any number of times.

Input parameters:

- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).

### `statica_bootstrap_finish` (~133 tokens)

Register project and run first analysis

Last step of connecting a project: re-check the capture, create the server project, mark the workspace ready, then run the full analysis and UPLOAD it (fullAnalysis). Deletes the backups taken by statica_bootstrap_guard once it succeeds. Covered by the user's approval of the connection; no separate upload question. stage=project means only server registration failed: fix the cause and call again, do not abort. Do not run pre-analyze afterwards. Pass on buildCommandWarning verbatim.

Input parameters:

- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).

### `statica_bootstrap_abort` (~123 tokens)

Cancel an unfinished connection

Undo an unfinished connection: restore files kept by statica_bootstrap_guard, then delete the wrapper and workspace. Refuses ready workspaces. For IDE/GUI substitution it cannot undo the IDE settings - walk the user through the guide's revert steps too. If ok is false the project is still modified: relay restore.failed and snapshotDir verbatim. Confirm with the user first.

Input parameters:

- `projectDir` (string, required): Absolute path of the project directory being analyzed (usually the session's working directory).
- `reason` (string): Why the connection is being cancelled.

### `statica_get_guide` (~112 tokens)

Read a STATICA procedure

Return the procedure STATICA's own skills follow, adapted for MCP: which tool runs each step, what to ask the user and where to stop. Read topic=bootstrap before connecting a project and follow it; it points to bootstrap-environments (C/C++ environments, compiler paths, substitution and revert steps) and bootstrap-other-languages (Java, Kotlin, Python, C#). upload explains when to upload; overview explains the plugin's scope.

Input parameters:

- `topic` (string, required): Which procedure to read.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/suresofttechnologies-statica-mcp/statica-mcp#diagnostics

## Score history

- 2026-11-21: 47
- 2026-11-20: 46
- 2026-11-19: 46
- 2026-11-18: 42
- 2026-11-17: 42
- 2026-11-16: 42
- 2026-11-15: 42
- 2026-11-14: 42
- 2026-11-13: 42
- 2026-11-12: 42
- 2026-11-11: 41
- 2026-11-10: 41

## Common questions

### What is the STATICA STATIC analysis tools MCP server?

STATICA STATIC analysis tools is an MCP server listed in the public MCP registry as io.github.SuresoftTechnologies/statica-mcp. Drive Suresoft STATIC analysis from a coding agent: connect, analyze, upload, manage rulesets. This page covers its MCPB bundle (https://github.com/SuresoftTechnologies/statica-plugin/releases/download/v0.1.0/statica-mcp.mcpb).

### Is the STATICA STATIC analysis tools MCP server safe to use?

STATICA STATIC analysis tools scores 47 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the STATICA STATIC analysis tools MCP server expose?

STATICA STATIC analysis tools exposes 24 tools: statica_doctor, statica_status, statica_pre_analyze, statica_set_auto_analysis, statica_scope_show, and 19 more. Their descriptions and schemas cost roughly 2,952 tokens of context every time the server is loaded.

### What licence is the STATICA STATIC analysis tools MCP server under?

STATICA STATIC analysis tools declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the STATICA STATIC analysis tools MCP server?

VerifyMCP ran 12 checks on STATICA STATIC analysis tools, covering Source repository, Provenance, License, Maintenance and 8 more. 4 items could not be completed, a gap on our side rather than a finding about STATICA STATIC analysis tools: Malware scan, Known CVEs, Install scripts and Dependency health. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an MCPB bundle, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Repository: https://github.com/SuresoftTechnologies/statica-plugin
- Changelog RSS feed: https://verifymcp.io/servers/suresofttechnologies-statica-mcp/statica-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/suresofttechnologies-statica-mcp/statica-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/suresofttechnologies-statica-mcp/statica-mcp.json
- HTML version of this page: https://verifymcp.io/servers/suresofttechnologies-statica-mcp/statica-mcp
