SITEBORNE Utility Network MCP server
net.siteborne/utilitysiteborne.netstreamable-httpv0.1.0Scanned
Machine-native utility network: verified evidence services for autonomous agents.
10 tools: 6 do something that can't be undone, 2 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 6
- Can send data out · 2
- 13 findings
Tools listed without sign-in. Remote posture
With Anlyon
6 tools here do something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the SITEBORNE Utility Network MCP server can do
The SITEBORNE Utility Network MCP server is published by siteborne.net, a domain the MCP Registry verified. It has 10 tools. It can do things that cannot be undone, such as sending, paying or publishing (siteborne_build_company_evidence_graph, siteborne_extract_document_evidence_json, siteborne_verify_agent_output, siteborne_build_company_evidence_graph_v3_candidate and 2 more) and create or change data (2 tools: siteborne_retrieve_verified_web_context and siteborne_retrieve_verified_web_context_v3_candidate), but cannot delete data. 2 tools only read.
6 tools bring in text other people can write (siteborne_build_company_evidence_graph, siteborne_retrieve_verified_web_context, siteborne_extract_document_evidence_json and 3 more); 2 tools can send data out of your system (siteborne_retrieve_verified_web_context and siteborne_retrieve_verified_web_context_v3_candidate).
The fixed checks matched 13 findings (long-description, annotation-conflict and credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 18, 2026, version 0.1.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
10 tools
Can't be undone 6Claude Code: ask
siteborne_build_company_evidence_graphBuild a proof-carrying graph of public company identity, SEC filings, website observations, regulatory mentions, and repository signals.Reads text others writeNo findings
Why it is in this group
- The input carries an amount (input.maximum_authorized_price.amount) and a currency, so it moves money.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Build a proof-carrying graph of public company identity, SEC filings, website observations, regulatory mentions, and repository signals. Use when: the request needs entity-level evidence synthesized across sources. Do not use when: one URL is the subject (use siteborne_retrieve_verified_web_context), one document is the subject (use siteborne_extract_document_evidence_json), or an existing agent output needs evaluation (use siteborne_verify_agent_output). Parameters: authoritative identifiers (cik, lei, isin, cusip, figi) resolve entities more reliably than company_name, ticker or domain alone, and combining them reduces ambiguity; requested_field_groups narrows provider work; maximum_authorized_price only constrains payment and never widens scope. Behavior: open-world: a paid request queries public data providers over the network and persists governed payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. This service is currently production-disabled and rejects execution. Economics: exact price of $0.0312 USD per request; the payment challenge requires that amount and the charge settles at exactly that amount. Failure: input that fails schema validation is rejected before any payment challenge; provider or service unavailability returns a structured MCP error. Returns: a company evidence graph with provenance, completeness, verification, and PCC context—not a raw webpage or document extraction.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
siteborne_build_company_evidence_graph_v3_candidateBuild a proof-carrying graph of public company identity, SEC filings, website observations, regulatory mentions, and repository signals.Reads text others writeNo findings
Why it is in this group
- The input carries an amount (input.maximum_authorized_price.amount) and a currency, so it moves money.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Build a proof-carrying graph of public company identity, SEC filings, website observations, regulatory mentions, and repository signals. Use when: the request needs entity-level evidence synthesized across sources. Do not use when: one URL is the subject (use siteborne_retrieve_verified_web_context), one document is the subject (use siteborne_extract_document_evidence_json), or an existing agent output needs evaluation (use siteborne_verify_agent_output). Parameters: authoritative identifiers (cik, lei, isin, cusip, figi) resolve entities more reliably than company_name, ticker or domain alone, and combining them reduces ambiguity; requested_field_groups narrows provider work; maximum_authorized_price only constrains payment and never widens scope. Behavior: open-world: a paid request queries public data providers over the network and persists governed payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. This service is currently production-disabled and rejects execution. Economics: exact price of $0.0312 USD per request; the payment challenge requires that amount and the charge settles at exactly that amount. Failure: input that fails schema validation is rejected before any payment challenge; provider or service unavailability returns a structured MCP error. Returns: a company evidence graph with provenance, completeness, verification, and PCC context—not a raw webpage or document extraction.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
siteborne_extract_document_evidence_jsonExtract and verify structured evidence from exactly one authorized artifact, prior SITEBORNE upload, or public document URL.Reads text others write3 findings
Why it is in this group
- The input carries an amount (input.maximum_authorized_price.amount) and a currency, so it moves money.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...ytes) or document_url (a public URL, no credentials). ocr_permission must be true before im..."
- Info
The input schema at properties.document_url.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.document_url.description: "...xactly one reference mode and never put credentials in this URL."
- Info
The description is 2,141 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...idence, integrity/provenance findings, and PCC verification—not an uploaded file."
Description, as the server wrote it Extract and verify structured evidence from exactly one authorized artifact, prior SITEBORNE upload, or public document URL. Use when: the source of truth is a PDF or supported image and the desired result is evidence JSON. Do not use when: a webpage alone is sufficient (use siteborne_retrieve_verified_web_context), company-wide public evidence is needed (use siteborne_build_company_evidence_graph), or an existing agent response needs evaluation (use siteborne_verify_agent_output). Parameters: provide exactly one reference mode: artifact_reference (an authorized stored artifact), upload_reference (a prior SITEBORNE upload handle, not document bytes) or document_url (a public URL, no credentials). ocr_permission must be true before image-based content is read by OCR, and OCR pages bill at the OCR tier; extraction_request.extract_tables and table_extraction_request request table extraction, and pages with tables bill at the table tier; declared_page_count and page_range are bounded by the page limit below; maximum_authorized_price only constrains payment. Behavior: open-world: a paid request may read governed artifact storage or fetch a public document URL, calls the document provider, and persists payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. This service is currently production-disabled and rejects execution. Economics: upto pricing: the payment challenge authorizes a maximum of $0.19 USD per job; the actual charge is measured per processed page (native-text $0.0098, OCR $0.0156, table $0.0238 per page, the highest applicable tier per page) and never exceeds the authorization. The authorization is a ceiling, not the charge. Documents are limited to 10 pages per job. Failure: schema-invalid input is rejected before any payment challenge; a document over the page limit, an unreadable or encrypted document, or an unavailable provider returns a structured MCP error. Returns: extracted document evidence, integrity/provenance findings, and PCC verification—not an uploaded file.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
siteborne_extract_document_evidence_json_v3_candidateExtract and verify structured evidence from exactly one authorized artifact, prior SITEBORNE upload, or public document URL.Reads text others write3 findings
Why it is in this group
- The input carries an amount (input.maximum_authorized_price.amount) and a currency, so it moves money.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...ytes) or document_url (a public URL, no credentials). ocr_permission must be true before im..."
- Info
The input schema at properties.document_url.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.document_url.description: "...xactly one reference mode and never put credentials in this URL."
- Info
The description is 2,141 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...idence, integrity/provenance findings, and PCC verification—not an uploaded file."
Description, as the server wrote it Extract and verify structured evidence from exactly one authorized artifact, prior SITEBORNE upload, or public document URL. Use when: the source of truth is a PDF or supported image and the desired result is evidence JSON. Do not use when: a webpage alone is sufficient (use siteborne_retrieve_verified_web_context), company-wide public evidence is needed (use siteborne_build_company_evidence_graph), or an existing agent response needs evaluation (use siteborne_verify_agent_output). Parameters: provide exactly one reference mode: artifact_reference (an authorized stored artifact), upload_reference (a prior SITEBORNE upload handle, not document bytes) or document_url (a public URL, no credentials). ocr_permission must be true before image-based content is read by OCR, and OCR pages bill at the OCR tier; extraction_request.extract_tables and table_extraction_request request table extraction, and pages with tables bill at the table tier; declared_page_count and page_range are bounded by the page limit below; maximum_authorized_price only constrains payment. Behavior: open-world: a paid request may read governed artifact storage or fetch a public document URL, calls the document provider, and persists payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. This service is currently production-disabled and rejects execution. Economics: upto pricing: the payment challenge authorizes a maximum of $0.19 USD per job; the actual charge is measured per processed page (native-text $0.0098, OCR $0.0156, table $0.0238 per page, the highest applicable tier per page) and never exceeds the authorization. The authorization is a ceiling, not the charge. Documents are limited to 10 pages per job. Failure: schema-invalid input is rejected before any payment challenge; a document over the page limit, an unreadable or encrypted document, or an unavailable provider returns a structured MCP error. Returns: extracted document evidence, integrity/provenance findings, and PCC verification—not an uploaded file.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
siteborne_verify_agent_outputEvaluate a supplied agent output against explicit claims, deterministic requirements, a required JSON Schema, and optional evidence.1 finding
Why it is in this group
- The description's first verb is "evaluate": a word for a change.
- The input carries an amount (input.maximum_authorized_price.amount) and a currency, so it moves money.
Findings
- Info
The description is 2,088 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...overall verification verdict, and PCC evidence—not newly gathered source content."
Description, as the server wrote it Evaluate a supplied agent output against explicit claims, deterministic requirements, a required JSON Schema, and optional evidence. Use when: the caller already has an output and needs a governed verification verdict. Do not use when: evidence must first be gathered from a company (use siteborne_build_company_evidence_graph), URL (use siteborne_retrieve_verified_web_context), or document (use siteborne_extract_document_evidence_json), or independent reproduction of the output is required (not available). Parameters: verification_mode must be standard; independent_reproduction is defined but unavailable and is rejected before any payment challenge, never downgraded to standard. required_schema must fit SITEBORNE JSON Schema Profile 1 or the request is rejected before payment; minimum_score sets the acceptance threshold; maximum_authorized_price only constrains payment and never relaxes verification policy. Behavior: closed-world: standard mode evaluates only the supplied claims, requirements, output and evidence with no outbound retrieval, and persists governed payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. The verification policy and verdict rules do not depend on price or maximum_authorized_price. This service is currently production-disabled and rejects execution. Economics: exact price of $0.017 USD per request in standard mode; the payment challenge requires that amount and the charge settles at exactly that amount. independent_reproduction mode has a governed price of $0.049 USD but is not available: it is rejected before any payment challenge and never substituted. Failure: an unsupported or oversized required_schema, schema-invalid input and unavailable modes are rejected before any payment challenge; a failed verification is a normal fail or conditional verdict, not an error. Returns: claim-level and deterministic-check results, an overall verification verdict, and PCC evidence—not newly gathered source content.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
siteborne_verify_agent_output_v3_candidateEvaluate a supplied agent output against explicit claims, deterministic requirements, a required JSON Schema, and optional evidence.1 finding
Why it is in this group
- The description's first verb is "evaluate": a word for a change.
- The input carries an amount (input.maximum_authorized_price.amount) and a currency, so it moves money.
Findings
- Info
The description is 2,088 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...overall verification verdict, and PCC evidence—not newly gathered source content."
Description, as the server wrote it Evaluate a supplied agent output against explicit claims, deterministic requirements, a required JSON Schema, and optional evidence. Use when: the caller already has an output and needs a governed verification verdict. Do not use when: evidence must first be gathered from a company (use siteborne_build_company_evidence_graph), URL (use siteborne_retrieve_verified_web_context), or document (use siteborne_extract_document_evidence_json), or independent reproduction of the output is required (not available). Parameters: verification_mode must be standard; independent_reproduction is defined but unavailable and is rejected before any payment challenge, never downgraded to standard. required_schema must fit SITEBORNE JSON Schema Profile 1 or the request is rejected before payment; minimum_score sets the acceptance threshold; maximum_authorized_price only constrains payment and never relaxes verification policy. Behavior: closed-world: standard mode evaluates only the supplied claims, requirements, output and evidence with no outbound retrieval, and persists governed payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. The verification policy and verdict rules do not depend on price or maximum_authorized_price. This service is currently production-disabled and rejects execution. Economics: exact price of $0.017 USD per request in standard mode; the payment challenge requires that amount and the charge settles at exactly that amount. independent_reproduction mode has a governed price of $0.049 USD but is not available: it is rejected before any payment challenge and never substituted. Failure: an unsupported or oversized required_schema, schema-invalid input and unavailable modes are rejected before any payment challenge; a failed verification is a normal fail or conditional verdict, not an error. Returns: claim-level and deterministic-check results, an overall verification verdict, and PCC evidence—not newly gathered source content.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Changes things 2Claude Code: ask
siteborne_retrieve_verified_web_contextRetrieve and verify evidence from one public web URL using direct HTTP retrieval.Reads text others writeCan send data out2 findings
Why it is in this group
- The name "siteborne_retrieve_verified_web_context" says "retrieve": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "siteborne_retrieve_verified_web_context" says "retrieve" and "web": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "retrieve" and "web": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.target_url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.target_url): a request to a URL can carry data to whoever runs it.
Findings
- Info
The description is 2,109 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...ns: normalized, source-attributed web context with verification and PCC evidence."
- Warn
The server marks "siteborne_retrieve_verified_web_context" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "siteborne_retrieve_verified_web_context" says "retrieve": a word for reading.
Description, as the server wrote it Retrieve and verify evidence from one public web URL using direct HTTP retrieval. Use when: the request is specifically about the content and provenance of a URL. Do not use when: evidence must be synthesized for a company (use siteborne_build_company_evidence_graph), extracted from an authorized document (use siteborne_extract_document_evidence_json), checked against an existing output contract (use siteborne_verify_agent_output), or the page requires JavaScript rendering (rendered retrieval is not available). Parameters: retrieval_mode must be direct; rendered is defined but unavailable and is rejected before any payment challenge, never substituted with direct retrieval. output_mode structured needs buyer_schema and field_selectors to be meaningful; redirect_policy and max_redirects bound redirect following; max_content_size bounds returned bytes; maximum_authorized_price only constrains payment and never changes retrieval scope. Behavior: open-world: a paid request performs bounded outbound HTTP retrieval of the target URL through a safe-egress boundary (private and loopback destinations are refused) and persists governed payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. Retrieval admission follows the governed runtime rate policy; no fixed public per-origin rate is promised. This service is currently production-disabled and rejects execution. Economics: exact price of $0.008 USD per request in direct mode; the payment challenge requires that amount and the charge settles at exactly that amount. rendered mode has a governed price of $0.029 USD but is not available: it is rejected before any payment challenge and never substituted. Failure: schema-invalid input and unavailable modes are rejected before any payment challenge; target-site errors, timeouts and unavailable retrieval return a structured MCP error and are never answered with a substitute result. Returns: normalized, source-attributed web context with verification and PCC evidence.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
siteborne_retrieve_verified_web_context_v3_candidateRetrieve and verify evidence from one public web URL using direct HTTP retrieval.Reads text others writeCan send data out2 findings
Why it is in this group
- The name "siteborne_retrieve_verified_web_context_v3_candidate" says "retrieve": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "siteborne_retrieve_verified_web_context_v3_candidate" says "retrieve" and "web": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "retrieve" and "web": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.target_url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.target_url): a request to a URL can carry data to whoever runs it.
Findings
- Info
The description is 2,109 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...ns: normalized, source-attributed web context with verification and PCC evidence."
- Warn
The server marks "siteborne_retrieve_verified_web_context_v3_candidate" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "siteborne_retrieve_verified_web_context_v3_candidate" says "retrieve": a word for reading.
Description, as the server wrote it Retrieve and verify evidence from one public web URL using direct HTTP retrieval. Use when: the request is specifically about the content and provenance of a URL. Do not use when: evidence must be synthesized for a company (use siteborne_build_company_evidence_graph), extracted from an authorized document (use siteborne_extract_document_evidence_json), checked against an existing output contract (use siteborne_verify_agent_output), or the page requires JavaScript rendering (rendered retrieval is not available). Parameters: retrieval_mode must be direct; rendered is defined but unavailable and is rejected before any payment challenge, never substituted with direct retrieval. output_mode structured needs buyer_schema and field_selectors to be meaningful; redirect_policy and max_redirects bound redirect following; max_content_size bounds returned bytes; maximum_authorized_price only constrains payment and never changes retrieval scope. Behavior: open-world: a paid request performs bounded outbound HTTP retrieval of the target URL through a safe-egress boundary (private and loopback destinations are refused) and persists governed payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. Retrieval admission follows the governed runtime rate policy; no fixed public per-origin rate is promised. This service is currently production-disabled and rejects execution. Economics: exact price of $0.008 USD per request in direct mode; the payment challenge requires that amount and the charge settles at exactly that amount. rendered mode has a governed price of $0.029 USD but is not available: it is rejected before any payment challenge and never substituted. Failure: schema-invalid input and unavailable modes are rejected before any payment challenge; target-site errors, timeouts and unavailable retrieval return a structured MCP error and are never answered with a substitute result. Returns: normalized, source-attributed web context with verification and PCC evidence.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 2Show 2 read-only tools
siteborne_get_quoteBuild a canonical x402 payment quote for one SITEBORNE service and exact request input.No findings
Why it is in this group
- The name "siteborne_get_quote" says "get": a word for reading.
Description, as the server wrote it Build a canonical x402 payment quote for one SITEBORNE service and exact request input. Use when: an agent needs the governed price, payee, network, asset, resource, expiry, and payment requirement before deciding whether to invoke a paid service. Do not use when: evidence work is required now (use the matching siteborne_build_company_evidence_graph, siteborne_retrieve_verified_web_context, siteborne_extract_document_evidence_json, or siteborne_verify_agent_output tool), or only availability is needed (use siteborne_get_service_health). Parameters: scheme must be the one scheme the service is offered under (company_evidence_graph.v2 exact, web_context_verified.v2 exact, document_evidence_json.v2 upto, verify_agent_output.v2 exact, company_evidence_graph.v3 exact, web_context_verified.v3 exact, document_evidence_json.v3 upto, verify_agent_output.v3 exact); any other scheme is rejected with scheme_not_offered. input is hashed, so the quote binds only that exact request. Behavior: quote-only and read-only; it hashes the proposed input, and does not execute the underlying paid service, verify payment, call a provider, create a Workflow, or settle. Economics: free of charge. The returned amount is the exact price, or for upto an authorized maximum whose actual_amount is null because the real charge is measured at settlement and never exceeds it. Failure: a mode that has a governed price but is unavailable returns retrieval_mode_unavailable or verification_mode_unavailable and no quote; a quote expires at expires_at. Returns: an expiring input-bound quote with its x402 payment requirement and the canonical economics block.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
siteborne_get_service_healthReport MCP server readiness and production-enable status for each SITEBORNE service.1 finding
Why it is in this group
- The name "siteborne_get_service_health" says "get": a word for reading.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...service tool). Behavior: read-only and credential-independent; it does not perform paid e..."
Description, as the server wrote it Report MCP server readiness and production-enable status for each SITEBORNE service. Use when: an agent must check protocol availability, tool count, or whether a service is currently production-enabled before selecting a paid tool. Do not use when: a quote is needed (use siteborne_get_quote) or company, web, document, or agent-output evidence work is required (use the corresponding SITEBORNE service tool). Behavior: read-only and credential-independent; it does not perform paid evidence work, create quotes, verify payment, call providers, write service state, create Workflows, or settle. Economics: free of charge; it never issues a payment challenge. Failure: it depends on no provider, so it does not fail because a provider is unavailable. Returns: the server and protocol versions plus truthful local, production, and external-publication status for all four evidence services.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write6
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:16 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 8
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 8 tools that change things (6 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://utility.siteborne.net/mcp: tools/list returned 10 tools to an anonymous client, including siteborne_build_company_evidence_graph (irreversible), siteborne_extract_document_evidence_json (irreversible), siteborne_verify_agent_output (irreversible), siteborne_build_company_evidence_graph_v3_candidate (irreversible), siteborne_extract_document_evidence_json_v3_candidate (irreversible) and 3 more
Findings
Matches of fixed checks, with the text they matched.
The server marks "siteborne_retrieve_verified_web_context" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "siteborne_retrieve_verified_web_context" says "retrieve": a word for reading.
The server marks "siteborne_retrieve_verified_web_context_v3_candidate" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "siteborne_retrieve_verified_web_context_v3_candidate" says "retrieve": a word for reading.
The description is 2,109 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...ns: normalized, source-attributed web context with verification and PCC evidence."
The description mentions "credentials".
What this check looks forMatched text
description: "...ytes) or document_url (a public URL, no credentials). ocr_permission must be true before im..."
The input schema at properties.document_url.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.document_url.description: "...xactly one reference mode and never put credentials in this URL."
The description is 2,141 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...idence, integrity/provenance findings, and PCC verification—not an uploaded file."
Show 7 more findingsShow fewer
The description is 2,088 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...overall verification verdict, and PCC evidence—not newly gathered source content."
The description is 2,109 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...ns: normalized, source-attributed web context with verification and PCC evidence."
The description mentions "credentials".
What this check looks forMatched text
description: "...ytes) or document_url (a public URL, no credentials). ocr_permission must be true before im..."
The input schema at properties.document_url.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.document_url.description: "...xactly one reference mode and never put credentials in this URL."
The description is 2,141 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...idence, integrity/provenance findings, and PCC verification—not an uploaded file."
The description is 2,088 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...overall verification verdict, and PCC evidence—not newly gathered source content."
The description mentions "credential".
What this check looks forMatched text
description: "...service tool). Behavior: read-only and credential-independent; it does not perform paid e..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http utility https://utility.siteborne.net/mcpclaude mcp add --transport http utility https://utility.siteborne.net/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__utility__siteborne_get_quote",
"mcp__utility__siteborne_get_service_health"
],
"ask": [
"mcp__utility__siteborne_build_company_evidence_graph",
"mcp__utility__siteborne_retrieve_verified_web_context",
"mcp__utility__siteborne_extract_document_evidence_json",
"mcp__utility__siteborne_verify_agent_output",
"mcp__utility__siteborne_build_company_evidence_graph_v3_candidate",
"mcp__utility__siteborne_retrieve_verified_web_context_v3_candidate",
"mcp__utility__siteborne_extract_document_evidence_json_v3_candidate",
"mcp__utility__siteborne_verify_agent_output_v3_candidate"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as utility. Review it before you use it.
Capability tags behind 6 rules
- mcp__utility__siteborne_build_company_evidence_graph untrusted-input
- mcp__utility__siteborne_retrieve_verified_web_context untrusted-input, outbound
- mcp__utility__siteborne_extract_document_evidence_json untrusted-input
- mcp__utility__siteborne_build_company_evidence_graph_v3_candidate untrusted-input
- mcp__utility__siteborne_retrieve_verified_web_context_v3_candidate untrusted-input, outbound
- mcp__utility__siteborne_extract_document_evidence_json_v3_candidate untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/net.siteborne/utility/verify?hash=029b1512c5778576375d887492da86c1a7d60ab245553a04784397db2fc5e371" | jq -e '.changed == false'Pinned hash 029b1512c577, from Nov 18, 2026, 21:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/net.siteborne/utility/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/net.siteborne/utility)Source: MCP Registry. Synced Oct 21, 2026, 18:53 UTC.
SITEBORNE Utility Network MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the SITEBORNE Utility Network MCP server safe?
- No scan can promise that. What its definitions show: 10 tools, 8 of which can change, send or delete something, and 13 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the SITEBORNE Utility Network MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the SITEBORNE Utility Network MCP server do things that cannot be undone?
- Yes. 6 tools can send, pay, publish or merge: siteborne_build_company_evidence_graph, siteborne_extract_document_evidence_json, siteborne_verify_agent_output, siteborne_build_company_evidence_graph_v3_candidate, siteborne_extract_document_evidence_json_v3_candidate and siteborne_verify_agent_output_v3_candidate.
What tools does the SITEBORNE Utility Network MCP server have?
- 10 tools: 6 irreversible, 2 write, 2 read. siteborne_build_company_evidence_graph, siteborne_extract_document_evidence_json, siteborne_verify_agent_output, siteborne_build_company_evidence_graph_v3_candidate, siteborne_extract_document_evidence_json_v3_candidate, siteborne_verify_agent_output_v3_candidate, siteborne_retrieve_verified_web_context, siteborne_retrieve_verified_web_context_v3_candidate and 2 more.
Does the SITEBORNE Utility Network MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the SITEBORNE Utility Network MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): siteborne_retrieve_verified_web_context and siteborne_retrieve_verified_web_context_v3_candidate.
Has the SITEBORNE Utility Network MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.