Agent Revenue Network MCP server
dev.workers.nadirventurelabs.agent-revenue-network/agent-revenue-networkagent-revenue-network.nadirventurelabs.workers.devstreamable-httpv0.7.0Scanned
Paid deterministic data-quality and execution-verification tools for AI agents.
18 tools: 3 do something that can't be undone, 10 change things and 5 only read.
- Reads private data · 1
- Reads text others write · 16
- Can send data out · 0
- 3 findings
Tools listed without sign-in. Remote posture
With Anlyon
3 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 Agent Revenue Network MCP server can do
The Agent Revenue Network MCP server is published by agent-revenue-network.nadirventurelabs.workers.dev, a domain the MCP Registry verified. It has 18 tools. It can do things that cannot be undone, such as sending, paying or publishing (job_contract_compile, execution_proof_pack and delivery_assurance) and create or change data (10 tools: score_opportunity, route_provider, json_normalize, object_contract_check and 6 more), but cannot delete data. 5 tools only read.
1 tool reads private data (tabular_diff); 16 tools bring in text other people can write (json_normalize, object_contract_check, json_schema_check and 13 more).
The fixed checks matched 3 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 15, 2026, version 0.7.0.
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.
18 tools
Can't be undone 3Claude Code: ask
delivery_assuranceRun one paid end-to-end AI agent delivery assurance workflow as a neutral work-acceptance layer instead of letting the buyer or worker judge its own delivery.Reads text others write1 finding
Why it is in this group
- The description's first verb is "run": a word for a change.
- The input carries an amount (input.contract.payment.amount) and a currency, so it moves money.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "delivery_assurance" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.
Description, as the server wrote it Run one paid end-to-end AI agent delivery assurance workflow as a neutral work-acceptance layer instead of letting the buyer or worker judge its own delivery. Supply privacy-preserving party references, objective work terms, named artifacts and all nine explicit release-gate outcomes. ARN compiles and hashes the contract, independently checks supported artifact criteria, screens bounded artifacts for exposed secret material, deterministically evaluates supplied gates, and—only after its verification fee settles—publishes an Ed25519-signed RELEASE_ELIGIBLE or HOLD_OR_DISPUTE receipt. Any agent can verify it offline with ARN's public JWKS. A free signed sandbox integration is available at /v1/integrations/delivery-assurance/sandbox and can never authorize settlement. ARN does not custody or transfer job funds. It does not perform a general malware scan, authenticate authorship, verify external facts, or certify caller-supplied legal or regulatory outcomes. This free MCP discovery call does not execute the advertised capability and does not charge; it returns the exact x402 endpoint, price and payment guide.
Annotations the server declares
- title: End-to-End AI Agent Delivery Assurance · Signed Settlement Receipt
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
execution_proof_packVerify AI agent work delivery against acceptance criteria with ARN's independent artifact-verification service.Reads text others write1 finding
Why it is in this group
- The input carries an amount (input.contract.payment.amount) and a currency, so it moves money.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "execution_proof_pack" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The input carries an amount (input.contract.payment.amount) and a currency, so it moves money.
Description, as the server wrote it Verify AI agent work delivery against acceptance criteria with ARN's independent artifact-verification service. Use the objective contract from job_contract_compile; paid execution recompiles it, hashes every supplied artifact, performs each supported JSON Schema, exact-value, required/forbidden-text or SHA-256 criterion, and returns APPROVED or QUARANTINED with per-check evidence and a tamper-evident pack hash. This verifies only the supplied contract and artifacts; it is not an AI-authorship detector, malware scan, factuality certificate or legal opinion. This free MCP discovery call does not execute the advertised capability and does not charge; it returns the exact x402 endpoint, price and payment guide for execution.
Annotations the server declares
- title: Verify AI Agent Work Delivery Against Acceptance Criteria · Proof Pack
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
job_contract_compileCompile an AI agent job contract with objective acceptance criteria into ARN's deterministic canonical job-contract format.Reads text others write1 finding
Why it is in this group
- The input carries an amount (input.payment.amount) and a currency, so it moves money.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "job_contract_compile" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The input carries an amount (input.payment.amount) and a currency, so it moves money.
Description, as the server wrote it Compile an AI agent job contract with objective acceptance criteria into ARN's deterministic canonical job-contract format. Supply a goal, deliverables and one or more supported machine-checkable criteria: bounded JSON Schema, exact JSON value, required or forbidden text, or SHA-256. Paid execution rejects ambiguous and unsupported fields, canonicalizes the contract and returns a SHA-256 contract hash. It does not claim work, execute it or move funds. Pair the result with execution_proof_pack after delivery. This free MCP discovery call does not execute the advertised capability and does not charge; it returns the exact x402 endpoint, price and payment guide for execution.
Annotations the server declares
- title: AI Agent Job Contract with Objective Acceptance Criteria · Compiler
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Changes things 10Claude Code: ask
dataset_profileDiscover deterministic data-quality profiling for 1-5,000 JSON-object rows.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 Discover deterministic data-quality profiling for 1-5,000 JSON-object rows. Paid execution counts field presence, missing and null values, observed primitive types, primitive cardinality and exact duplicate rows without modifying input; use schema_infer to draft a flat-record contract or tabular_validate to enforce one. This is not statistical inference. This free MCP discovery call does not execute the advertised capability and does not charge; it returns the exact x402 endpoint, price and payment guide for execution.
Annotations the server declares
- title: JSON Dataset Profiling · Data Quality
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
json_normalizeDiscover deterministic JSON normalization for any JSON value: paid HTTP execution recursively sorts object keys, preserves array order and scalar values, and returns normalized str…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 Discover deterministic JSON normalization for any JSON value: paid HTTP execution recursively sorts object keys, preserves array order and scalar values, and returns normalized structure plus a deterministic JSON string. Use it for stable comparisons, cache keys and repeatable payloads; use json_diff to identify changes, and never treat this as RFC 8785/JCS canonicalization. This free MCP discovery call does not execute the advertised capability and does not charge; it returns the exact x402 endpoint, price and payment guide for execution.
Annotations the server declares
- title: JSON Normalization · Stable Key Ordering
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
json_schema_checkDiscover recursive JSON Schema checking for objects, arrays and scalars with exact JSON-path errors from ARN's bounded recursive JSON Schema subset.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 Discover recursive JSON Schema checking for objects, arrays and scalars with exact JSON-path errors from ARN's bounded recursive JSON Schema subset. The supplied schema may combine type unions, required/properties, additionalProperties=false, items, enum/const, numeric bounds, string length or safe patterns, array bounds/uniqueness and property-count bounds; unsupported keywords fail closed. Prefer object_contract_check for a new simple top-level contract. This free MCP discovery call does not execute the advertised capability and does not charge; it returns the exact x402 endpoint, price and payment guide for execution.
Annotations the server declares
- title: Recursive JSON Schema Checking · Deterministic Validation
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
object_contract_checkDiscover deterministic top-level JSON field validation for API payloads, automation and AI-agent handoffs.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 Discover deterministic top-level JSON field validation for API payloads, automation and AI-agent handoffs. The value must be an object; schema.required finds absent fields, schema.properties.<field>.type finds primitive type mismatches, and additionalProperties=false reports unknown fields. Prefer this for new simple contracts and use json_schema_check for nested or recursive constraints. This free MCP discovery call does not execute the advertised capability and does not charge; it returns the exact x402 endpoint, price and payment guide for execution.
Annotations the server declares
- title: JSON Field Validation
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
result_dedupeDiscover deterministic duplicate removal for JSON-record arrays and structured research results.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 Discover deterministic duplicate removal for JSON-record arrays and structured research results. Supply one to eight identity fields: paid execution forms a typed composite key, preserves the first occurrence in original order, and reports exact input, output and duplicate counts; use dataset_profile when you only need duplicate measurement. This free MCP discovery call does not execute the advertised capability and does not charge; it returns the exact x402 endpoint, price and payment guide for execution.
Annotations the server declares
- title: Remove Duplicate JSON Rows · Research Result Dedupe
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
route_providerRank up to 1,000 caller-supplied providers by quality, success rate, price and latency, returning one selection plus at most three alternates.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Rank up to 1,000 caller-supplied providers by quality, success rate, price and latency, returning one selection plus at most three alternates. Candidates marked unhealthy or priced above requirements.maxPrice are excluded; quality defaults to successRate and an empty eligible set returns selected=null with a reason. Use this free read-only calculation only with comparable metrics you already hold because it neither discovers providers nor verifies measurements. A successful selection includes an optional buyer-controlled verify_execution handoff; it does not charge or initiate payment.
Annotations the server declares
- title: Route Provider
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
schema_inferDiscover conservative JSON Schema inference from multiple flat JSON-object records for imports, API contract drafting or validation setup.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 Discover conservative JSON Schema inference from multiple flat JSON-object records for imports, API contract drafting or validation setup. Paid execution emits stable observed primitive/null type unions and marks a field required only when every row contains a non-null value; nested objects and arrays are rejected instead of guessed. Use dataset_profile for descriptive counts or json_schema_check to validate against an existing schema. This free MCP discovery call does not execute the advertised capability and does not charge; it returns the exact x402 endpoint, price and payment guide for execution.
Annotations the server declares
- title: Infer JSON Schema from Flat Records · Conservative Contract
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
score_opportunityCalculate risk-adjusted expected profit, margin and eligibility for one proposed opportunity before execution.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Calculate risk-adjusted expected profit, margin and eligibility for one proposed opportunity before execution. Supply revenue, execution cost and any tool costs, fees or failure loss in one consistent monetary unit; omitted tool costs and fees are zero, while omitted failure loss defaults to total costs. Use this free read-only calculation as an economics screen, never as proof of funding, escrow, requirements or buyer legitimacy. An eligible result includes an optional buyer-controlled verify_execution handoff; it does not charge or initiate payment.
Annotations the server declares
- title: Score Opportunity Economics
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
verified_translationDiscover QA-verified translation for up to 2,000 characters on calibrated EN→ES, EN→FR, ES→FR and FR→ES routes.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 Discover QA-verified translation for up to 2,000 characters on calibrated EN→ES, EN→FR, ES→FR and FR→ES routes. sourceLang defaults to EN, targetLang selects ES or FR, protectedTerms must remain unchanged, and optional context, domain or locale hints guide approved memory and wording; live locale research is excluded. This free MCP discovery call does not execute the advertised capability and does not charge; it returns the exact x402 endpoint, price and payment guide for execution.
Annotations the server declares
- title: Verified Translation · Canadian French / Spanish / French
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
verify_executionDiscover deterministic acceptance checking for an automated task or agent execution across nine explicit functional, security, privacy, copyright, regulatory, transaction-integrity…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 Discover deterministic acceptance checking for an automated task or agent execution across nine explicit functional, security, privacy, copyright, regulatory, transaction-integrity, abuse, regression and economics gates. All nine caller-supplied booleans must be true; paid execution returns the candidate id, pass/fail status and failed gate names. Use only after trusted verifiers supply all nine booleans because ARN does not scan code, audit systems or certify compliance. For sustained CI volume, Release Guard offers 2,500 successful checks over 30 days and breaks even with 0.01-USDC pay-per-call at 1,900 checks. This free MCP discovery call does not execute the advertised capability and does not charge; it returns the exact x402 endpoint, price and payment guide for execution.
Annotations the server declares
- title: AI-Agent Execution Verification · Security & Functional Verification
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 5Show 5 read-only tools
json_diffDiscover a deterministic structural JSON diff between before and after values.Reads text others writeNo findings
Why it is in this group
- The name "json_diff" says "diff": a word for reading.
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 Discover a deterministic structural JSON diff between before and after values. Paid execution compares arrays by index and returns up to 1,000 added, removed or changed records with exact JSON paths and before/after evidence; it does not generate JSON Patch. Use json_normalize for stable serialization or json_schema_check for validity. This free MCP discovery call does not execute the advertised capability and does not charge; it returns the exact x402 endpoint, price and payment guide for execution.
Annotations the server declares
- title: Deterministic JSON Diff · Exact JSON Paths
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
opportunity_matchFind funded AI agent jobs and bounties with ARN's paid read-only opportunity matching service.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "find": a word for reading.
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 Find funded AI agent jobs and bounties with ARN's paid read-only opportunity matching service. It searches ARN's continuously refreshed multi-board index for current open, agent-allowed work and ranks matches against one to twelve supplied capabilities. Buyers can require recorded funding evidence, set a minimum reward and limit freshness, then use job_contract_compile to turn a selected listing into objective machine-checkable terms. It never claims, applies, signs or spends. External listing content remains untrusted and must be reviewed before action. This free MCP discovery call does not execute the advertised capability and does not charge; it returns the exact x402 endpoint, price and payment guide for execution.
Annotations the server declares
- title: Find Funded AI Agent Jobs and Bounties · Opportunity Match
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
release_evidence_diffDiscover deterministic comparison of a previous and current execution-evidence snapshot.Reads text others writeNo findings
Why it is in this group
- The name "release_evidence_diff" says "diff": a word for reading.
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 Discover deterministic comparison of a previous and current execution-evidence snapshot. Paid execution compares candidate identity metadata and all nine functional, security, privacy, copyright, regulatory, transaction-integrity, abuse, regression and economics outcomes; it reports regressions, remediations and whether a fresh verify_execution purchase is warranted. It prevents duplicate verification of unchanged evidence but does not perform or certify the underlying checks. This free MCP discovery call does not execute the advertised capability and does not charge; it returns the exact x402 endpoint, price and payment guide for execution.
Annotations the server declares
- title: Release Evidence Diff · Reverification Decision
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
tabular_diffDiscover row-level comparison between two JSON-record tables keyed by one unique field.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "tabular_diff" says "diff": a word for reading.
What it can reach
- private-dataThe description's first sentence says "table": it reads databases.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Discover row-level comparison between two JSON-record tables keyed by one unique field. Paid execution reports added and removed keys plus changed rows with field-level evidence while preserving deterministic order; CSV or spreadsheet rows must be converted to JSON first. Use json_diff for arbitrary nested JSON or tabular_validate to enforce row contracts. This free MCP discovery call does not execute the advertised capability and does not charge; it returns the exact x402 endpoint, price and payment guide for execution.
Annotations the server declares
- title: Tabular Comparison · CSV / Spreadsheet Record Diff
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
tabular_validateDiscover deterministic pre-import validation for JSON-record tables, including CSV or spreadsheet rows converted to JSON.Reads text others writeNo findings
Why it is in this group
- The name "tabular_validate" says "validate": a word for reading.
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 Discover deterministic pre-import validation for JSON-record tables, including CSV or spreadsheet rows converted to JSON. Paid execution checks every row for required columns and declared primitive types and returns bounded row-and-field errors; use object_contract_check for one object or json_schema_check for recursive constraints. This free MCP discovery call does not execute the advertised capability and does not charge; it returns the exact x402 endpoint, price and payment guide for execution.
Annotations the server declares
- title: Tabular Validation · CSV / Spreadsheet Pre-Import Check
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
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 outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write16
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- 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, 18:53 UTC, unchanged since Nov 20, 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
- 15
- 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 15 tools that change things (4 irreversible, 11 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://agent-revenue-network.nadirventurelabs.workers.dev/mcp: tools/list returned 20 tools to an anonymous client, including delivery_assurance_sandbox (irreversible), job_contract_compile (irreversible), execution_proof_pack (irreversible), delivery_assurance (irreversible), score_opportunity (write) and 10 more
Posture changes
- Nov 20, 2026
- Tools that change things, listed without credentials: 13 to 15
- Nov 13, 2026
- Tools that change things, listed without credentials: 12 to 13
- Nov 6, 2026
- Tools that change things, listed without credentials: 10 to 12
Findings
Matches of fixed checks, with the text they matched.
The server marks "job_contract_compile" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The input carries an amount (input.payment.amount) and a currency, so it moves money.
The server marks "execution_proof_pack" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The input carries an amount (input.contract.payment.amount) and a currency, so it moves money.
The server marks "delivery_assurance" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 13 -> 15.View diff
- Tools that change things, listed without credentials: 13 to 15
Tools1 added, 2 changed.+1 added~2 changedView diff
- Added:delivery_assuranceCan't be undone
- Changed:route_providerChanges thingsdescription
- Changed:score_opportunityChanges thingsdescription
PostureRemote posture changed. Tools that change things, listed without credentials: 12 -> 13.View diff
- Tools that change things, listed without credentials: 12 to 13
PostureRemote posture changed. Tools that change things, listed without credentials: 10 -> 12.View diff
- Tools that change things, listed without credentials: 10 to 12
Tools3 added.+3 addedView diff
- Added:execution_proof_packCan't be undone
- Added:job_contract_compileCan't be undone
- Added:opportunity_matchOnly reads
Install
Pinned to version 0.7.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-revenue-network https://agent-revenue-network.nadirventurelabs.workers.dev/mcpclaude mcp add --transport http agent-revenue-network https://agent-revenue-network.nadirventurelabs.workers.dev/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__agent-revenue-network__json_diff",
"mcp__agent-revenue-network__release_evidence_diff",
"mcp__agent-revenue-network__opportunity_match",
"mcp__agent-revenue-network__tabular_diff",
"mcp__agent-revenue-network__tabular_validate"
],
"ask": [
"mcp__agent-revenue-network__score_opportunity",
"mcp__agent-revenue-network__route_provider",
"mcp__agent-revenue-network__json_normalize",
"mcp__agent-revenue-network__object_contract_check",
"mcp__agent-revenue-network__json_schema_check",
"mcp__agent-revenue-network__dataset_profile",
"mcp__agent-revenue-network__verify_execution",
"mcp__agent-revenue-network__job_contract_compile",
"mcp__agent-revenue-network__execution_proof_pack",
"mcp__agent-revenue-network__delivery_assurance",
"mcp__agent-revenue-network__verified_translation",
"mcp__agent-revenue-network__result_dedupe",
"mcp__agent-revenue-network__schema_infer"
],
"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 agent-revenue-network. Review it before you use it.
Capability tags behind 16 rules
- mcp__agent-revenue-network__json_normalize untrusted-input
- mcp__agent-revenue-network__object_contract_check untrusted-input
- mcp__agent-revenue-network__json_schema_check untrusted-input
- mcp__agent-revenue-network__json_diff untrusted-input
- mcp__agent-revenue-network__dataset_profile untrusted-input
- mcp__agent-revenue-network__verify_execution untrusted-input
- mcp__agent-revenue-network__release_evidence_diff untrusted-input
- mcp__agent-revenue-network__opportunity_match untrusted-input
- mcp__agent-revenue-network__job_contract_compile untrusted-input
- mcp__agent-revenue-network__execution_proof_pack untrusted-input
- mcp__agent-revenue-network__delivery_assurance untrusted-input
- mcp__agent-revenue-network__verified_translation untrusted-input
- mcp__agent-revenue-network__result_dedupe untrusted-input
- mcp__agent-revenue-network__schema_infer untrusted-input
- mcp__agent-revenue-network__tabular_diff private-data, untrusted-input
- mcp__agent-revenue-network__tabular_validate 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/dev.workers.nadirventurelabs.agent-revenue-network/agent-revenue-network/verify?hash=c1db40aef8321c2a741a5bc6dcb1d76fc5fcc5f32e8a04196db04acaa55eaf39" | jq -e '.changed == false'Pinned hash c1db40aef832, from Nov 15, 2026, 05:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.workers.nadirventurelabs.agent-revenue-network/agent-revenue-network/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.workers.nadirventurelabs.agent-revenue-network/agent-revenue-network)Source: MCP Registry. Synced Oct 21, 2026, 18:12 UTC.
Agent Revenue Network MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agent Revenue Network MCP server safe?
- No scan can promise that. What its definitions show: 18 tools, 13 of which can change, send or delete something, and 3 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 Agent Revenue 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 Agent Revenue Network MCP server do things that cannot be undone?
- Yes. 3 tools can send, pay, publish or merge: job_contract_compile, execution_proof_pack and delivery_assurance.
What tools does the Agent Revenue Network MCP server have?
- 18 tools: 3 irreversible, 10 write, 5 read. job_contract_compile, execution_proof_pack, delivery_assurance, score_opportunity, route_provider, json_normalize, object_contract_check, json_schema_check and 10 more.
Does the Agent Revenue Network MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agent Revenue Network MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Agent Revenue Network MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 15, 2026. Every change is on this page and in its Atom feed.