Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Agent Revenue Network

REMOTE · AGENT-REVENUE-NETWORK.NADIRVENTURELABS.WORKERS.DEV

Paid deterministic data-quality and execution-verification tools for AI agents.

+1 this week 74 Trust /100

Last scanned (19 hours ago)

Scores higher than 66% of remote servers

Reachable. Last reached 16 Oct 2026.

Category Testing and QA

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security69
Transport & Reachability100
Schema Quality & AI Usability76
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1727 tokens (~132/item across 13 items; 13 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 Management47
  • Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
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; "result_dedupe" implies "remove" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Fail
  • An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Changelog

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.

  • 15 Oct 26 −1
    • Tool “json_schema_check” rewrote its description, which is the text the model reads security
    • Tool “result_dedupe” rewrote its description, which is the text the model reads security
    • Tool “schema_infer” rewrote its description, which is the text the model reads security
    • Destructive annotations: pass → 0 functional
    • “json_schema_check” reworded the description of “schema” cosmetic
    • “json_schema_check” reworded the description of “value” cosmetic
    • Tool “json_schema_check” changed its title: Validate JSON · Schema Subset → Validate JSON · Recursive Schema Subset cosmetic
    • Tool “result_dedupe” changed its title: Deduplicate JSON Results → Remove Duplicate JSON Rows · Research Result Dedupe cosmetic
    • Tool “schema_infer” changed its title: Infer JSON Record Schema → Infer JSON Schema · Flat Record Contract cosmetic
  • 14 Oct 26 0
    • “route_provider” reworded the description of “providers” cosmetic

    1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.

  • 13 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 33. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Oct 26 0
    • New tool “result_dedupe” functional
    • New tool “schema_infer” functional
  • 9 Oct 26 +1
    • Tool “verify_execution” rewrote its description, which is the text the model reads security
    • Schema quality: 119 → 133 ▼ functional
    • Tool “verify_execution” changed its title: Automated Task Security & Functional Verification → AI-Agent Execution Verification · Security & Functional Verification cosmetic
  • 7 Oct 26 0
    • Server version: 1.2.3 → 1.2.4 functional
  • 6 Oct 26 +1
    • Schema quality: 1111 → 1316 ▼ functional
Diagnostics

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 16 Oct 2026 · Probed https://agent-revenue-network.nadirventurelabs.workers.dev/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=nadirventurelabs.workers.dev CN=YE2,O=Let's Encrypt,C=US 24 Sept 2026 23 Dec 2026 ECDSA 256 ECDSA-SHA384 56586201e4aba4992a09c4acc0a4665192c
SANs: *.nadirventurelabs.workers.dev, nadirventurelabs.workers.dev
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of agent-revenue-network.nadirventurelabs.workers.dev. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
dev. present 60074 8 Verified
workers.dev. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains
content-security-policy default-src 'none'; style-src 'unsafe-inline'; frame-ancestors 'none'; base-uri 'none'; form-action 'none'
x-content-type-options nosniff
x-frame-options DENY
referrer-policy no-referrer
permissions-policy camera=(), microphone=(), geolocation=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://agent-revenue-network.nadirventurelabs.workers.dev/mcp Verified 200
http (plaintext) http://agent-revenue-network.nadirventurelabs.workers.dev/mcp Inconclusive 405
MCP tools · 13 exposed · ~1,648 tokens

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 →

Tool Tokens
dataset_profile ~100

JSON dataset profiling and data quality: profile 1-5,000 JSON-object rows for presence, missing/null counts, observed primitive types, primitive cardinality, and exact duplicate rows. Use for quick deterministic data-quality inspection, not statistical inference or schema validation. This MCP call is read-only and returns x402 execution instructions without charging.

NameTypeReqDescription
rowsarrayyes1-5,000 JSON objects. Rows are analyzed in memory and are not modified.
NameTypeReqDescription
endpointstringyesARN HTTP path to POST the same tool arguments to for paid execution.
instructionstringyesHow to execute the capability after receiving the payment requirement.
paymentGuidestringyesPublic setup guide with a working x402 v2 Base-mainnet client example.
paymentRequiredbooleanyesAlways true for paid ARN capabilities exposed over MCP.
priceobjectyes–
protocolstringyesPayment protocol required by the HTTP execution endpoint.

No examples provided.

json_diff ~86

Compare JSON values with a deterministic structural JSON diff. Use for machine-readable change detection; arrays are compared by index and the result is capped at 1,000 changes, so this is not a JSON Patch generator. This MCP call is read-only and returns x402 execution instructions without charging.

NameTypeReqDescription
after–yesNew JSON value to compare with before.
before–yesOriginal JSON value.
NameTypeReqDescription
endpointstringyesARN HTTP path to POST the same tool arguments to for paid execution.
instructionstringyesHow to execute the capability after receiving the payment requirement.
paymentGuidestringyesPublic setup guide with a working x402 v2 Base-mainnet client example.
paymentRequiredbooleanyesAlways true for paid ARN capabilities exposed over MCP.
priceobjectyes–
protocolstringyesPayment protocol required by the HTTP execution endpoint.

No examples provided.

json_normalize ~105

Perform JSON normalization by recursively sorting object keys to produce stable structure and a deterministic JSON string. Use for comparisons, cache keys, repeatable payloads, or pre-signing preparation; do not use as RFC 8785/JCS canonicalization. This MCP call is read-only and does not charge: it returns the x402 endpoint and current price for execution.

NameTypeReqDescription
value–yesAny JSON value to normalize. Object keys are recursively sorted; array order and scalar values are preserved.
NameTypeReqDescription
endpointstringyesARN HTTP path to POST the same tool arguments to for paid execution.
instructionstringyesHow to execute the capability after receiving the payment requirement.
paymentGuidestringyesPublic setup guide with a working x402 v2 Base-mainnet client example.
paymentRequiredbooleanyesAlways true for paid ARN capabilities exposed over MCP.
priceobjectyes–
protocolstringyesPayment protocol required by the HTTP execution endpoint.

No examples provided.

json_schema_check ~170

Validate JSON objects, arrays or scalars with a bounded recursive JSON Schema subset. Supports type unions, required, nested properties, additionalProperties=false, array items, enum, const, minimum/maximum, min/max length, safe regular-expression patterns, min/max items, uniqueItems and property-count bounds. Unsupported keywords fail closed. For a simple top-level object contract, prefer object_contract_check. This MCP call is read-only and returns x402 execution instructions without charging.

NameTypeReqDescription
schemaobjectyesBounded recursive JSON Schema subset: type (including unions), required, properties, additionalProperties=false, items, enum, const, numeric bounds, string length/pattern, array length/uniqueness, an…
value–yesAny JSON value to validate.
NameTypeReqDescription
endpointstringyesARN HTTP path to POST the same tool arguments to for paid execution.
instructionstringyesHow to execute the capability after receiving the payment requirement.
paymentGuidestringyesPublic setup guide with a working x402 v2 Base-mainnet client example.
paymentRequiredbooleanyesAlways true for paid ARN capabilities exposed over MCP.
priceobjectyes–
protocolstringyesPayment protocol required by the HTTP execution endpoint.

No examples provided.

object_contract_check ~109

Identify missing or invalid JSON fields by checking one object's top-level required fields, allowed fields, and declared field types. Prefer this for new API/pipeline shape contracts; it is intentionally smaller and easier to reason about than full JSON Schema. This MCP call is read-only and returns x402 execution instructions without charging.

NameTypeReqDescription
schemaobjectyesTop-level contract definition. Only required, properties.<field>.type, and additionalProperties=false are evaluated.
valueobjectyesJSON object to check.
NameTypeReqDescription
endpointstringyesARN HTTP path to POST the same tool arguments to for paid execution.
instructionstringyesHow to execute the capability after receiving the payment requirement.
paymentGuidestringyesPublic setup guide with a working x402 v2 Base-mainnet client example.
paymentRequiredbooleanyesAlways true for paid ARN capabilities exposed over MCP.
priceobjectyes–
protocolstringyesPayment protocol required by the HTTP execution endpoint.

No examples provided.

result_dedupe ~102

Remove duplicate rows from JSON arrays and structured research results using one to eight caller-selected identity fields while preserving the first occurrence. Use for deterministic result deduplication before import, analysis or agent handoff. This MCP discovery call is read-only and returns x402 execution instructions without charging.

NameTypeReqDescription
keysarrayyesOne to eight field names that together form the record identity.
rowsarrayyesJSON object rows to deduplicate while preserving the first occurrence.
NameTypeReqDescription
endpointstringyesARN HTTP path to POST the same tool arguments to for paid execution.
instructionstringyesHow to execute the capability after receiving the payment requirement.
paymentGuidestringyesPublic setup guide with a working x402 v2 Base-mainnet client example.
paymentRequiredbooleanyesAlways true for paid ARN capabilities exposed over MCP.
priceobjectyes–
protocolstringyesPayment protocol required by the HTTP execution endpoint.

No examples provided.

route_provider ~108

Rank the provider candidates supplied in this call using quality, reliability, price, and latency, while excluding unhealthy or over-budget entries. Use only when you already have comparable provider metrics; this tool does not discover providers or verify the supplied measurements. It is read-only.

NameTypeReqDescription
providersarrayyesUp to 1,000 provider candidates to rank. An empty list returns no eligible provider; unhealthy candidates are excluded.
requirementsobject–Routing constraints. maxPrice is the currently enforced constraint.
NameTypeReqDescription
alternatesarrayyesUp to three next-ranked eligible providers.
reasonstringyesHuman-readable explanation of the routing result.
selectedobject|nullyesHighest-ranked eligible provider, including its computed score, or null.

No examples provided.

schema_infer ~89

Infer a conservative JSON schema from flat JSON records using observed primitive and null field types. Use for deterministic data-contract discovery before validation or import; nested objects and arrays are rejected rather than guessed. This MCP discovery call is read-only and returns x402 execution instructions without charging.

NameTypeReqDescription
rowsarrayyesFlat JSON object rows used to infer observed primitive/null field types. Nested objects and arrays are rejected.
NameTypeReqDescription
endpointstringyesARN HTTP path to POST the same tool arguments to for paid execution.
instructionstringyesHow to execute the capability after receiving the payment requirement.
paymentGuidestringyesPublic setup guide with a working x402 v2 Base-mainnet client example.
paymentRequiredbooleanyesAlways true for paid ARN capabilities exposed over MCP.
priceobjectyes–
protocolstringyesPayment protocol required by the HTTP execution endpoint.

No examples provided.

score_opportunity ~160

Estimate risk-adjusted expected profit and margin for one opportunity before execution. Use it as an economics screen, not as proof that funding, escrow, requirements, or buyer legitimacy are valid. It is read-only and returns expectedProfit, margin, and eligibility using ARN's current minimums.

NameTypeReqDescription
executionCostnumberyesDirect execution cost excluding tools and fees.
failureLossnumber–Loss incurred on failure. Defaults internally to total execution/tool/fee cost.
failureProbabilitynumber–Estimated probability of failure, from 0 to 1.
feesnumber–Optional platform/payment fees.
revenuenumberyesGross payment expected if the task succeeds.
toolCostnumber–Optional third-party/tool cost.
NameTypeReqDescription
eligiblebooleanyesTrue when expected profit is at least 0.05 and margin is at least 0.20.
expectedProfitnumberyesRisk-adjusted expected profit in the same monetary unit as the inputs.
marginnumberyesExpected profit divided by revenue; 0 when revenue is 0.

No examples provided.

tabular_diff ~116

Compare two keyed JSON record sets and identify added, removed and changed rows. Use for row-level comparison keyed by one unique field; for arbitrary JSON structures use json_diff. CSV or spreadsheet rows must be converted to JSON first. This MCP discovery call is read-only and returns x402 execution instructions without charging.

NameTypeReqDescription
afterarrayyesNew keyed JSON record set to compare with before.
beforearrayyesOriginal keyed JSON record set.
keystringyesField name used as the unique record identity in both datasets.
NameTypeReqDescription
endpointstringyesARN HTTP path to POST the same tool arguments to for paid execution.
instructionstringyesHow to execute the capability after receiving the payment requirement.
paymentGuidestringyesPublic setup guide with a working x402 v2 Base-mainnet client example.
paymentRequiredbooleanyesAlways true for paid ARN capabilities exposed over MCP.
priceobjectyes–
protocolstringyesPayment protocol required by the HTTP execution endpoint.

No examples provided.

tabular_validate ~141

Validate JSON-record tables before import, automation or handoff. Use for row-by-row required-column and primitive-type checks; for one object use object_contract_check, or use json_schema_check when an existing JSON-Schema-shaped contract must be checked. CSV or spreadsheet rows must be converted to JSON first. This MCP discovery call is read-only and returns x402 execution instructions without charging.

NameTypeReqDescription
requiredarray–Optional field names that must be present on every row.
rowsarrayyesJSON object rows to validate. Between 1 and 5,000 rows.
typesobject–Optional mapping of field name to required JSON primitive type.
NameTypeReqDescription
endpointstringyesARN HTTP path to POST the same tool arguments to for paid execution.
instructionstringyesHow to execute the capability after receiving the payment requirement.
paymentGuidestringyesPublic setup guide with a working x402 v2 Base-mainnet client example.
paymentRequiredbooleanyesAlways true for paid ARN capabilities exposed over MCP.
priceobjectyes–
protocolstringyesPayment protocol required by the HTTP execution endpoint.

No examples provided.

verified_translation ~216

Translate text with verified Spanish translation and French translation, up to 2,000 characters across calibrated EN→ES, EN→FR, ES→FR and FR→ES routes using protected-token preservation, semantic back-translation verification, and approved translation memory when available. A locale hint such as fr-CA can guide Canadian French wording, but live locale research is not included. This MCP call is read-only and returns x402 execution instructions without charging.

NameTypeReqDescription
contextstring–Optional tone/domain context.
domainstring–Optional domain label used for approved translation-memory lookup.
localestring–Optional locale hint such as ES-419 or fr-CA. This verified tier does not yet perform live web locale research.
protectedTermsarray–Terms/names that must remain unchanged.
sourceLangstring–Source language.
targetLangstringyesTarget language. The source/target pair must be a currently calibrated route.
textstringyesSource text or Markdown to translate.
NameTypeReqDescription
endpointstringyesARN HTTP path to POST the same tool arguments to for paid execution.
instructionstringyesHow to execute the capability after receiving the payment requirement.
paymentGuidestringyesPublic setup guide with a working x402 v2 Base-mainnet client example.
paymentRequiredbooleanyesAlways true for paid ARN capabilities exposed over MCP.
priceobjectyes–
protocolstringyesPayment protocol required by the HTTP execution endpoint.

No examples provided.

verify_execution ~146

Check whether an automated task or agent execution passed explicit functional, security, privacy, copyright, regulatory, transaction-integrity, abuse, regression, and economics gates. Use for post-execution agent-job acceptance or a release gate only AFTER independent trusted verifiers supply all nine booleans; this tool evaluates submitted evidence rather than independently scanning code, auditing systems, or certifying legal compliance. This MCP call is read-only and returns x402 execution instructions without charging.

NameTypeReqDescription
candidateobjectyesCandidate metadata. candidate.id is returned when present; candidate contents are not independently inspected.
checksobjectyesExplicit boolean outcomes from trusted upstream verifiers. Every gate must be true to approve.
NameTypeReqDescription
endpointstringyesARN HTTP path to POST the same tool arguments to for paid execution.
instructionstringyesHow to execute the capability after receiving the payment requirement.
paymentGuidestringyesPublic setup guide with a working x402 v2 Base-mainnet client example.
paymentRequiredbooleanyesAlways true for paid ARN capabilities exposed over MCP.
priceobjectyes–
protocolstringyesPayment protocol required by the HTTP execution endpoint.

No examples provided.

Install

How do I install the Agent Revenue Network MCP server?

Agent Revenue Network is a hosted endpoint at https://agent-revenue-network.nadirventurelabs.workers.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · agent-revenue-network.nadirventurelabs.workers.dev

# add to Claude Code
claude mcp add --transport http dev-workers-nadirventurelabs-agent-revenue-netwo 'https://agent-revenue-network.nadirventurelabs.workers.dev/mcp'
Common questions

What is the Agent Revenue Network MCP server?

Agent Revenue Network is an MCP server listed in the public MCP registry as dev.workers.nadirventurelabs.agent-revenue-network/agent-re…. Paid deterministic data-quality and execution-verification tools for AI agents. This page covers its hosted endpoint (https://agent-revenue-network.nadirventurelabs.workers.dev/mcp).

Is the Agent Revenue Network MCP server safe to use?

Agent Revenue Network scores 74 out of 100 on VerifyMCP. 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 Agent Revenue Network MCP server expose?

Agent Revenue Network exposes 13 tools: score_opportunity, route_provider, json_normalize, object_contract_check, json_schema_check, and 8 more. Their descriptions and schemas cost roughly 1,648 tokens of context every time the server is loaded.

Does the Agent Revenue Network MCP server require authentication?

No. We connected to Agent Revenue Network without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Agent Revenue Network MCP server still maintained?

Agent Revenue Network is still listed as active in the MCP registry. We last reached this channel on 16 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.