Dagon Inference
NPM · DAGON-MCP · 2 COMPONENTS
Uncensored LLM inference: list models, chat, create keys, buy credits with Solana USDC.
Available components
Last scanned (19 hours ago)
Scores higher than 37% 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 Security89
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects uuid 8.3.2, reached via @solana/web3.js > jayson > uuid. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 51 of 148 dependencies flagged as unhealthy (1 deprecated). View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- 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 10 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability75
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 694 tokens (~115/item across 6 items; 6 tools + 0 resources), lean.Pass
- 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 Coverage96
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 87% of tool parameters carry a description.Partial
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "dagon_chat" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 6 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 (15)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
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.
- 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.
- 11 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 10 Nov 26 50
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/dagon-mcp@0.1.0
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 4 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-528h-pc64-c93x | CVE-2026-71429 | medium | CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-hqr4-qq8f-hg3x | CVE-2026-104182 | medium | CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-mjw6-4jj6-33hc | CVE-2026-104183 | medium | CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L | yes |
| GHSA-w5hq-g745-h8pq | CVE-2026-41907 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:N | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 148 packages
| Packages resolved | 148 |
|---|---|
| Deprecated | 1 |
| Stale | 50 |
| 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 →
dagon_balance Check Dagon credit balance ~63
Show the credit balance of a Dagon account key in USD: total credits, total usage, available (GET /v1/credits).
| Name | Type | Req | Description |
|---|---|---|---|
| api_key | string | – | Dagon account key (gk_...). Defaults to the DAGON_API_KEY environment variable. |
No output schema declared.
No examples provided.
dagon_buy_credits Buy Dagon credits with Solana USDC ~226
Buy credits for the configured Dagon account, paid in USDC on Solana. The server checks that the gateway's transaction is exactly the USDC payment to the configured treasury (DAGON_TREASURY_WALLET). If the MCP server has a wallet (DAGON_WALLET_SECRET_KEY), it then signs and confirms it (submitting it itself unless the purchase is fee sponsored, in which case the payment service adds the fee payer's signature and submits it). Otherwise it returns the verified unsigned transaction for payer_wallet to sign; then call dagon_confirm_purchase with signed_transaction (fee sponsored: do not submit it yourself) or with the signature of the transaction you submitted (not fee sponsored).
| Name | Type | Req | Description |
|---|---|---|---|
| amount_usd | number | yes | Amount to buy in USD (whole cents, e.g. 5 or 12.5). |
| chain | string | – | Payment chain. Only 'solana' (USDC) is supported. |
| payer_wallet | string | – | Base58 Solana address that pays. Required when the server has no wallet configured. |
No output schema declared.
No examples provided.
dagon_chat Chat with a Dagon model ~144
Send a chat completion to a Dagon model (POST /v1/chat/completions, non-streaming) and return the reply. Spends credits.
| Name | Type | Req | Description |
|---|---|---|---|
| api_key | string | – | Dagon account key (gk_...). Defaults to the DAGON_API_KEY environment variable. |
| max_tokens | integer | – | – |
| messages | array | – | Full conversation, OpenAI chat format. Use this or prompt. |
| model | string | yes | Model id from dagon_models. |
| prompt | string | – | User message. Use this or messages. |
| system | string | – | Optional system prompt, prepended to the conversation. |
| temperature | number | – | – |
No output schema declared.
No examples provided.
dagon_confirm_purchase Confirm a Dagon credit purchase ~152
Report a dagon_buy_credits payment you signed yourself so the configured account is credited (POST /v1/credits/purchase/confirm). Fee sponsored: pass signed_transaction, the base64 wallet-signed transaction, without submitting it (the payment service adds the fee payer's signature and submits it; resending the same one is safe). Not fee sponsored: submit it yourself and pass its signature.
| Name | Type | Req | Description |
|---|---|---|---|
| purchase_id | string | yes | purchase_id returned by dagon_buy_credits. |
| signature | string | – | Base58 Solana transaction signature of the payment you submitted (not fee sponsored). |
| signed_transaction | string | – | Base64 wallet-signed transaction of a fee-sponsored purchase, not submitted. |
No output schema declared.
No examples provided.
dagon_create_key Create a Dagon API key ~75
Create a new Dagon account key (POST /v1/keys). The secret is shown only once: store it securely (e.g. as DAGON_API_KEY) and never paste it into shared chats or files under version control.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Label for the key, up to 80 characters. |
No output schema declared.
No examples provided.
dagon_models List Dagon models ~34
List the models available on Dagon Inference, with their pricing (GET /v1/models). No API key needed.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
How do I install the Dagon Inference MCP server?
Dagon Inference runs locally as an npm package, launched with npx -y dagon-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 · dagon-mcp
claude mcp add inkwell-finance-dagon-mcp -- npx -y dagon-mcp
What is the Dagon Inference MCP server?
Dagon Inference is an MCP server listed in the public MCP registry as io.github.inkwell-finance/dagon-mcp. Uncensored LLM inference: list models, chat, create keys, buy credits with Solana USDC. This page covers its npm package (dagon-mcp).
Is the Dagon Inference MCP server safe to use?
Dagon Inference scores 65 out of 100 on VerifyMCP. We recorded 4 known advisories 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 Dagon Inference MCP server expose?
Dagon Inference exposes 6 tools: dagon_models, dagon_balance, dagon_create_key, dagon_buy_credits, dagon_confirm_purchase, dagon_chat. Their descriptions and schemas cost roughly 694 tokens of context every time the server is loaded.
Is the Dagon Inference MCP server still maintained?
Dagon Inference 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 Dagon Inference MCP server under?
Dagon Inference 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 Dagon Inference MCP server?
VerifyMCP ran 15 checks on Dagon Inference, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about Dagon Inference: 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.