CoreForge Media
NPM · COREFORGE-MEDIA-MCP
CoreForge media tools: speech-to-text, document parsing, translation, embeddings. x402 pay-per-call.
Available components
Last scanned (15 hours ago)
Scores higher than 29% of npm servers
Category AI and Machine Learning
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. How we score → Why this is hard to score →
Supply Chain Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 31 of 113 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
- Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 15 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability74
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 943 tokens (~117/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
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.
Checks we ran (14)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Schema quality
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (2)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.
- Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 9 Nov 26 59
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Analysed npm/coreforge-media-mcp@1.0.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 113 packages
| Packages resolved | 113 |
|---|---|
| Stale | 30 |
| No linked repository | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
chat_completion ~111
OpenAI-compatible chat completion served by CoreForge Inference (local Qwen3-8B) with hard server-side token and daily caps. Paid via x402 ($0.002 USDC on Base) when a payer wallet is configured; otherwise returns the payment requirements.
| Name | Type | Req | Description |
|---|---|---|---|
| max_tokens | integer | – | Requested max tokens (server-side cap applies) |
| messages | array | yes | Chat messages, OpenAI style: [{role, content}] |
| model | string | – | Model name (server allowlist applies) |
No output schema declared.
No examples provided.
document_parse ~121
Parse one PDF or image document (up to 25 MB) into clean markdown plus structured JSON with a local open-source document model (Granite-Docling). Documents never leave CoreForge infrastructure. Paid via x402 ($0.10 USDC on Base) when a payer wallet is configured; otherwise returns the payment requirements.
| Name | Type | Req | Description |
|---|---|---|---|
| documentBase64 | string | – | Base64-encoded document |
| documentUrl | string | – | URL of the document (alternative to documentBase64) |
| filename | string | – | Filename hint, e.g. report.pdf |
No output schema declared.
No examples provided.
embeddings ~92
Compute 768-dim text embeddings (BGE base, run locally) for one text or a batch of up to 256 texts. OpenAI-style response shape. Paid via x402 ($0.002 USDC on Base) when a payer wallet is configured; otherwise returns the payment requirements.
| Name | Type | Req | Description |
|---|---|---|---|
| input | – | yes | One text, or an array of texts (max 256, each max 8,192 chars) |
No output schema declared.
No examples provided.
image_generate ~148
Generate one draft/concept image (default 1024×1024) from a text prompt with FLUX.1-schnell on a local GPU. Concept quality; text rendering in images is not guaranteed. Paid via x402 ($0.05 USDC on Base) when a payer wallet is configured; otherwise returns the payment requirements.
| Name | Type | Req | Description |
|---|---|---|---|
| height | integer | – | Height in px (default 1024) |
| prompt | string | yes | Image prompt (max 1,000 chars) |
| seed | integer | – | Seed for reproducibility |
| steps | integer | – | Diffusion steps (default 4) |
| width | integer | – | Width in px (default 1024) |
No output schema declared.
No examples provided.
page_to_markdown ~74
Fetch a web page and return clean, model-ready markdown (title + extracted content, up to 100k characters). Paid via x402 ($0.002 USDC on Base) when a payer wallet is configured; otherwise returns the payment requirements.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | The page URL (http/https) |
No output schema declared.
No examples provided.
rerank ~107
Rerank up to 100 documents against a query with a local BGE cross-encoder reranker; returns relevance scores (optionally just the top N). Paid via x402 ($0.005 USDC on Base) when a payer wallet is configured; otherwise returns the payment requirements.
| Name | Type | Req | Description |
|---|---|---|---|
| documents | array | yes | Documents to score (max 100) |
| query | string | yes | The query to rank against |
| top_n | integer | – | Return only the top N documents |
No output schema declared.
No examples provided.
speech_to_text ~174
Transcribe one audio file (up to 15 minutes) with CoreForge Speech (local faster-whisper): transcript text, detected language, duration and word-level segments. Provide an audio URL or base64 audio. Paid via x402 ($0.40 USDC on Base) when a payer wallet is configured; otherwise returns the payment requirements.
| Name | Type | Req | Description |
|---|---|---|---|
| audioBase64 | string | – | Base64-encoded audio (alternative to audioUrl) |
| audioUrl | string | – | URL of the audio file to transcribe |
| durationSeconds | number | – | Declared duration in seconds (max 900) |
| filename | string | – | Filename hint, e.g. interview.mp3 (used with audioBase64) |
| language | string | – | Language hint, e.g. 'en' (auto-detected when omitted) |
No output schema declared.
No examples provided.
translate_text ~116
Translate up to 5,000 characters of text into a target language with a local MADLAD-400 model. Suited to listings, blurbs and metadata. Paid via x402 ($0.01 USDC on Base) when a payer wallet is configured; otherwise returns the payment requirements.
| Name | Type | Req | Description |
|---|---|---|---|
| source | string | – | Source language code (auto-detected when omitted) |
| target | string | yes | Target language code, e.g. 'es', 'fr', 'de' |
| text | string | yes | Text to translate |
No output schema declared.
No examples provided.
How do I install the CoreForge Media MCP server?
CoreForge Media runs locally as an npm package, launched with npx -y coreforge-media-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · coreforge-media-mcp
claude mcp add shaficodes25-coreforge-media -- npx -y coreforge-media-mcp
What is the CoreForge Media MCP server?
CoreForge Media is an MCP server listed in the public MCP registry as io.github.ShafiCodes25/coreforge-media. CoreForge media tools: speech-to-text, document parsing, translation, embeddings. x402 pay-per-call. This page covers its npm package (coreforge-media-mcp).
Is the CoreForge Media MCP server safe to use?
CoreForge Media scores 59 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares no install or post-install scripts. 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 CoreForge Media MCP server expose?
CoreForge Media exposes 8 tools: speech_to_text, document_parse, page_to_markdown, translate_text, embeddings, and 3 more. Their descriptions and schemas cost roughly 943 tokens of context every time the server is loaded.
Is the CoreForge Media MCP server still maintained?
CoreForge Media is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the CoreForge Media MCP server under?
CoreForge Media 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 CoreForge Media MCP server?
VerifyMCP ran 14 checks on CoreForge Media, covering Malware scan, Known CVEs, Install scripts, Dependency health and 10 more. 2 items could not be completed, a gap on our side rather than a finding about CoreForge Media: Security disclosure and Stability. 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 npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.