← Back to search

io.github.CSOAI-ORG/image-metadata-ai-mcp

CSOAI-ORG Scanned 16d ago

AI-powered image metadata ai MCP server for agents. Supports detect format, get dimensions, ...

C
73.3 / 100

Versions

1.0.1latest
first seen Jun 5, 2026
1.0.4
first seen May 19, 2026
PermissionsTool SafetyAuthAnnotationsCode QualityStabilitySpecVuln HistoryAuthorTransparencyCommunity

Tools 4

detect_format
annotations: none low

Detect image format from file path or base64 data. Args: file_path: Path to image file base64_data: Base64-encoded image data (first 100 chars sufficient) Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

api_key str file_path str base64_data str
get_dimensions
annotations: none low

Get width and height of an image file (supports PNG, JPEG, GIF, BMP). Args: file_path: Path to image file Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

api_key str file_path str
read_exif
annotations: none low

Read EXIF metadata from a JPEG image file. Args: file_path: Path to JPEG image file Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

api_key str file_path str
strip_metadata
annotations: none low

Strip all metadata from an image file for privacy. Args: file_path: Path to source image output_path: Output path (default: adds '_clean' suffix) Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

api_key str file_path str output_path str

Permissions 3

network medium
Server uses network capabilities via: urllib
filesystem low
Server uses filesystem capabilities via: open(), os
env_vars low
Server uses env_vars capabilities via: os.environ

Scan Findings 73

low
Tool 'detect_format' has no annotations annotation_checker · 100%
low
Tool 'get_dimensions' has no annotations annotation_checker · 100%
low
Tool 'read_exif' has no annotations annotation_checker · 100%
low
Tool 'strip_metadata' has no annotations annotation_checker · 100%
high
Remote transport without authentication auth_checker · 70%
info
Sandbox failed to start for behavioral verification behavioral_verifier · 100%
medium
Vulnerable dependency: mcp@1.0.0 (GHSA-3qhf-m339-9g5v) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (GHSA-9h52-p55h-vw2f) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (GHSA-j975-95f5-7wqh) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (GHSA-jpw9-pfvf-9f58) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (GHSA-vj7q-gjh5-988w) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (PYSEC-2026-1616) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (PYSEC-2026-1617) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (PYSEC-2026-1618) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (PYSEC-2026-3482) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (PYSEC-2026-3483) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-3f63-hfp8-52jq) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-44wm-f244-xhp3) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-45hq-cxwh-f6vc) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-4x4j-2g7c-83w6) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-5x94-69rx-g8h2) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-62p4-gmf7-7g93) dependency_analyzer · 95%
low
Permission: env_vars access detected permission_analyzer · 90%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-6r8x-57c9-28j4) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-8ghj-p4vj-mr35) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-8v84-f9pq-wr9x) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-8vj2-vxx3-667w) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-9hw9-ch79-4vh6) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-9j59-75qj-795w) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-fj7v-r99m-22gq) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-j7hp-h8jx-5ppr) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-jjj6-mw9f-p565) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-m2vv-5vj5-2hm7) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-phj9-mv4w-65pm) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-r73j-pqj5-w3x7) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-vjc4-5qp5-m44j) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-wjx4-4jcj-g98j) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (GHSA-xj96-63gp-2gmr) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2022-168) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2022-42979) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2022-42980) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2023-175) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2023-227) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2026-165) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2026-1793) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2026-1794) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2026-2253) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2026-2254) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2026-2255) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2026-2256) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2026-2257) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2026-2874) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2026-3451) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2026-3453) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2026-3454) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2026-3493) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2026-3494) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2026-3495) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2026-3496) dependency_analyzer · 95%
medium
Vulnerable dependency: pillow@9.0.0 (PYSEC-2026-457) dependency_analyzer · 95%
info
package.json metadata manifest_parser · 100%
info
pyproject.toml metadata manifest_parser · 100%
info
SBOM generated: 1 components sbom_generator · 100%
medium
No build provenance detected (SLSA L0) slsa_assessor · 90%
info
Tool: detect_format manifest_parser · 90%
info
Tool: get_dimensions manifest_parser · 90%
info
Tool: read_exif manifest_parser · 90%
info
Tool: strip_metadata manifest_parser · 90%
info
Transport: streamable-http manifest_parser · 80%
info
Required env vars (1) manifest_parser · 80%
info
Sandbox failed to start for output poisoning scan output_poisoning · 100%
medium
Permission: network access detected permission_analyzer · 80%
low
Permission: filesystem access detected permission_analyzer · 80%