Softbot Studio agent tools
NPM · SOFTBOT-MCP
Pay-per-call x402 agent tools (USDC): web reader, token/wallet/email/site checks, screenshots, PDFs.
Available components
Last scanned (10 hours ago)
Scores higher than 41% of npm servers
Category Web Scraping
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 Security99
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 34 of 239 dependencies flagged as unhealthy. 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 1 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability78
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1154 tokens (~115/item across 10 items; 10 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 Management7
- Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage94
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 81% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 10 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
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.
- 17 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 0 to 3. That category is still filling its 30-day observation window: 0 days of observed history at the previous scan, 1 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Oct 26 70
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 18 Oct 2026 · Analysed npm/softbot-mcp@0.2.0
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 →
Dependencies 239 packages
| Packages resolved | 239 |
|---|---|
| Stale | 34 |
| 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 →
check_domain Email domain check ~109
Whether a domain can receive mail (MX/A, null MX), is disposable/free/typo, its SPF/DMARC/DKIM posture and registration age. Use when vetting a company or sender domain rather than a specific mailbox. Price: $0.002 USDC per call. First 3 calls free per wallet.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | yes | Single domain, e.g. example.com |
| dry_run | boolean | – | If true, only report the price; nothing is paid. |
No output schema declared.
No examples provided.
check_email Email address check ~118
Email address verdict (deliverable_likely/risky/invalid) from syntax, MX, disposable list, role address, typo suggestion, SPF/DMARC/DKIM and domain age. Does not contact the mailbox. Use when about to send to, sign up with, or accept an email address. Price: $0.002 USDC per call. First 3 calls free per wallet.
| Name | Type | Req | Description |
|---|---|---|---|
| dry_run | boolean | – | If true, only report the price; nothing is paid. |
| string | yes | Single email address |
No output schema declared.
No examples provided.
check_solana_token Solana token safety check ~127
Solana token safety verdict (safe/caution/avoid) with a 0-100 risk score and reasons: mint/freeze authority, Token-2022 extensions, holder concentration, age, DEX liquidity. Use when about to buy, swap, accept or recommend an unfamiliar Solana token. Not financial advice. Price: $0.01 USDC per call. First 3 calls free per wallet.
| Name | Type | Req | Description |
|---|---|---|---|
| dry_run | boolean | – | If true, only report the price; nothing is paid. |
| mint | string | yes | Solana token mint address (base58) |
No output schema declared.
No examples provided.
check_wallet Solana wallet profile ~117
Solana wallet verdict (established/new/suspicious/inactive) from SOL balance, holdings, age, recent activity, program-account detection, bot-pattern heuristic and OFAC sanctions match. Use when about to pay, airdrop to, trade with or trust an unknown wallet. Price: $0.005 USDC per call. First 3 calls free per wallet.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | Solana wallet address (base58) |
| dry_run | boolean | – | If true, only report the price; nothing is paid. |
No output schema declared.
No examples provided.
check_website Website trust check ~130
Website trust verdict (trustworthy_likely/caution/risky) from domain age, DNS, HTTPS and redirects, security headers, phishing/malware lists, brand lookalike detection and tech fingerprint. Use when about to visit, log in to, pay on, or recommend an unfamiliar site or link. Price: $0.003 USDC per call. First 3 calls free per wallet.
| Name | Type | Req | Description |
|---|---|---|---|
| dry_run | boolean | – | If true, only report the price; nothing is paid. |
| url | string | yes | URL or bare domain, e.g. https://example.com/login |
No output schema declared.
No examples provided.
extract_structured Extract structured page data ~162
Reader Pro: return machine-readable data from a page without an LLM: meta/OpenGraph, JSON-LD, HTML tables as row objects, links, emails/phones/socials, headings, images, plus optional CSS-selector fields. Use when you need facts, tables or contact details from a page rather than prose. Price: $0.004 USDC per call. First 3 calls free per wallet.
| Name | Type | Req | Description |
|---|---|---|---|
| dry_run | boolean | – | If true, only report the price; nothing is paid. |
| fields | object | – | Map name -> CSS selector (append ' @attr' for an attribute). Max 20. |
| include | array | – | Sections to return (default: all) |
| url | string | yes | Public http(s) URL |
No output schema declared.
No examples provided.
page_to_pdf Save page as PDF ~108
Render a public page in headless Chrome and return it as an A4 PDF (embedded resource, base64). Use when you need a printable or archivable copy of a page, receipt or article. Price: $0.01 USDC per call. First 3 calls free per wallet.
| Name | Type | Req | Description |
|---|---|---|---|
| dry_run | boolean | – | If true, only report the price; nothing is paid. |
| url | string | yes | Public http(s) URL |
| wait_ms | integer | – | – |
No output schema declared.
No examples provided.
read_url Read web page ~100
Fetch a public web page and return clean markdown plus title and metadata (respects robots.txt). Use when you need to read or summarize the text of an article, docs page or any URL. Price: $0.003 USDC per call (Solana). First 3 calls free per wallet.
| Name | Type | Req | Description |
|---|---|---|---|
| dry_run | boolean | – | If true, only report the price; nothing is paid. |
| url | string | yes | Public http(s) URL |
No output schema declared.
No examples provided.
screenshot_url Screenshot web page ~146
Render a public page in headless Chrome and return a PNG/JPEG screenshot as an image. Use when you need to see what a page actually looks like (layout, visual check, proof, charts). Price: $0.01 USDC per call. First 3 calls free per wallet.
| Name | Type | Req | Description |
|---|---|---|---|
| dry_run | boolean | – | If true, only report the price; nothing is paid. |
| format | string | – | – |
| full_page | boolean | – | Capture full scroll height (max 8000px) |
| height | integer | – | – |
| url | string | yes | Public http(s) URL |
| wait_ms | integer | – | – |
| width | integer | – | – |
No output schema declared.
No examples provided.
softbot_status Softbot session status ~37
Show this session's USDC spend, budget, paying wallet address and tool prices. Free; use before paid calls to check remaining budget.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
How do I install the Softbot Studio agent tools MCP server?
Softbot Studio agent tools runs locally as an npm package, launched with npx -y softbot-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 · softbot-mcp
claude mcp add softbot-studio-softbot-mcp -- npx -y softbot-mcp
What is the Softbot Studio agent tools MCP server?
Softbot Studio agent tools is an MCP server listed in the public MCP registry as io.github.softbot-studio/softbot-mcp. Pay-per-call x402 agent tools (USDC): web reader, token/wallet/email/site checks, screenshots, PDFs. This page covers its npm package (softbot-mcp).
Is the Softbot Studio agent tools MCP server safe to use?
Softbot Studio agent tools scores 71 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 18 October 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 Softbot Studio agent tools MCP server expose?
Softbot Studio agent tools exposes 10 tools: read_url, extract_structured, check_solana_token, check_email, check_domain, and 5 more. Their descriptions and schemas cost roughly 1,154 tokens of context every time the server is loaded.
Is the Softbot Studio agent tools MCP server still maintained?
Softbot Studio agent tools is still listed as active in the MCP registry. We last reached this channel on 18 October 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 Softbot Studio agent tools MCP server under?
Softbot Studio agent 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.