ScrubMyText + Agent Infrastructure MCP server
com.scrubmytext/toolsscrubmytext.comstreamable-httpv7.5.0Scanned
49 deterministic tools for text integrity, agent control, and contextual quality evidence.
49 tools: 3 can delete or cancel things, 1 do something that can't be undone, 37 change things and 8 only read.
- Reads private data · 1
- Reads text others write · 1
- Can send data out · 0
- 3 findings
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here can delete or cancel things and 1 does 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 ScrubMyText + Agent Infrastructure MCP server can do
The ScrubMyText + Agent Infrastructure MCP server is published by scrubmytext.com, a domain the MCP Registry verified. It has 49 tools. It can delete or cancel things (3 tools: release_action, delete_signal and cancel_approval), do things that cannot be undone, such as sending, paying or publishing (manage_context_status) and create or change data (37 tools: scrub_text, scan_untrusted_text, redact_sensitive_text, detect_secrets and 33 more). 8 tools only read.
1 tool reads private data (get_signal_events); 1 tool brings in text other people can write (get_signal_events).
The fixed checks matched 3 findings (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 14, 2026, version 7.5.0.
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.
49 tools
Deletes or cancels 3Claude Code: deny
cancel_approvalPaid: cancel a pending human approval request so its link can no longer approve the action.No findings
Why it is in this group
- The name "cancel_approval" says "cancel": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Paid: cancel a pending human approval request so its link can no longer approve the action.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
delete_signalPaid: immediately delete a signal inbox and all stored event bodies.No findings
Why it is in this group
- The name "delete_signal" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Paid: immediately delete a signal inbox and all stored event bodies.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
release_actionPaid: release an uncompleted action lock using its lock_id so another attempt can safely acquire it.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 destructive (destructiveHint: true).
Description, as the server wrote it Paid: release an uncompleted action lock using its lock_id so another attempt can safely acquire it.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
Can't be undone 1Claude Code: ask
manage_context_statusPublish, inspect, supersede, dispute, or revoke digest-only context status so downstream agents can stop using stale inputs.No findings
Why it is in this group
- The name "manage_context_status" says "status": a word for reading.
- The description's first verb is "publish": a word for a change that another call does not undo.
Description, as the server wrote it Publish, inspect, supersede, dispute, or revoke digest-only context status so downstream agents can stop using stale inputs. Stores no context body and does not invalidate copies outside this service. Subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
Changes things 37Claude Code: ask
anchor_context_traceCreate or inspect an immutable provenance anchor from a context digest, parent digests, and processing stage.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Create or inspect an immutable provenance anchor from a context digest, parent digests, and processing stage. No context content is stored. Production; subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
check_agent_readinessDeterministically check a supplied MCP server card against a narrow, published integration contract.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 Deterministically check a supplied MCP server card against a narrow, published integration contract. The service does not fetch arbitrary URLs and does not certify security or correctness. Free or paid.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
check_approvalPaid: check whether a human approval request is pending, approved, rejected, expired, or cancelled.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 Paid: check whether a human approval request is pending, approved, rejected, expired, or cancelled.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
complete_actionPaid: mark the current lock completed and preserve the idempotency record for its configured retention period.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.
Description, as the server wrote it Paid: mark the current lock completed and preserve the idempotency record for its configured retention period.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
create_signalUse when an agent must wait for an external callback, webhook, job completion, or asynchronous event.No findings
Why it is in this group
- The name "create_signal" says "create": a word for a change.
Description, as the server wrote it Use when an agent must wait for an external callback, webhook, job completion, or asynchronous event. Subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
detect_secretsUse before an agent logs, stores, or forwards text that may contain credentials.1 finding
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.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...ores, or forwards text that may contain credentials. Finds likely API keys, private keys, J..."
Description, as the server wrote it Use before an agent logs, stores, or forwards text that may contain credentials. Finds likely API keys, private keys, JWTs, cloud credentials, and secret patterns without echoing values. Trial, subscription, or x402 pay-per-call.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
fingerprint_actionUse before retryable work to derive a stable SHA-256 action fingerprint and idempotency key from an action name, optional scope, and JSON arguments.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 Use before retryable work to derive a stable SHA-256 action fingerprint and idempotency key from an action name, optional scope, and JSON arguments. Object key order does not affect the result. Returns no input values and stores nothing. Free or paid.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
lock_actionUse immediately before a consequential agent action to atomically claim an idempotency key so retries cannot execute it twice.No findings
Why it is in this group
- The name "lock_action" says "lock": a word for a change.
Description, as the server wrote it Use immediately before a consequential agent action to atomically claim an idempotency key so retries cannot execute it twice. Subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
lock_action_intentUse immediately before a consequential retryable action when no stable idempotency key exists.No findings
Why it is in this group
- The name "lock_action_intent" says "lock": a word for a change.
Description, as the server wrote it Use immediately before a consequential retryable action when no stable idempotency key exists. Deterministically fingerprints the action and arguments, atomically claims that key, and returns safe_to_execute. Repeat calls with equivalent object-key ordering return the same fingerprint and cannot acquire a second active lock. Subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
manage_action_challengeCreate, inspect, consume, or cancel a digest-bound cooling-off window.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Create, inspect, consume, or cancel a digest-bound cooling-off window. A bearer challenger can veto before the deadline; afterward the owner can atomically consume one execution right during a bounded window. This is exception handling, not affirmative consent or legal approval. Subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
manage_action_compensationBind a compensating-action digest before execution, record that the primary action executed, and atomically mark compensation once.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.
Description, as the server wrote it Bind a compensating-action digest before execution, record that the primary action executed, and atomically mark compensation once. Stores digests only and does not perform either action. Subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
manage_action_quorumCreate, inspect, consume, or cancel an N-of-M bearer authorization quorum.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Create, inspect, consume, or cancel an N-of-M bearer authorization quorum. Each unique bearer can decide once; only a successful one-time consume grants an execution right. Subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
manage_action_reconciliationOpen, inspect, append digest-only evidence to, or resolve a discrepancy between expected and observed action outcomes.No findings
Why it is in this group
- The description's first verb is "open": a word for a change.
Description, as the server wrote it Open, inspect, append digest-only evidence to, or resolve a discrepancy between expected and observed action outcomes. Production; subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
manage_agent_escalationCreate, inspect, or cancel a digest-only incident with a private bearer operator link and deterministic response and resolution SLA state.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Create, inspect, or cancel a digest-only incident with a private bearer operator link and deterministic response and resolution SLA state. Link delivery remains the caller’s responsibility. Subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
manage_agent_stopSet, inspect, or clear a durable stop signal for a hashed agent or workflow key.No findings
Why it is in this group
- The name "manage_agent_stop" says "stop": a word for a change.
Description, as the server wrote it Set, inspect, or clear a durable stop signal for a hashed agent or workflow key. Callers should fail closed whenever stopped is true. Production; subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
manage_attention_budgetCreate, inspect, reserve, release, or close a finite review-capacity pool with per-subject caps, retry-safe reservations, and protected priority capacity.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Create, inspect, reserve, release, or close a finite review-capacity pool with per-subject caps, retry-safe reservations, and protected priority capacity. Subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
manage_authority_delegationIssue, consume, inspect, or revoke a narrow bearer capability bound to one action fingerprint and a maximum use count.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.
Description, as the server wrote it Issue, consume, inspect, or revoke a narrow bearer capability bound to one action fingerprint and a maximum use count. This is a technical capability, not identity proof or a legal delegation. Production; subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
manage_context_rightsIssue, inspect, evaluate, or revoke a digest-bound machine-readable context-rights envelope.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.
Description, as the server wrote it Issue, inspect, evaluate, or revoke a digest-bound machine-readable context-rights envelope. It is a technical policy signal, not legal advice or proof of ownership. Subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
manage_disclosure_budgetCreate, inspect, record against, or close a cumulative disclosure budget with total, per-recipient, and per-category limits.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Create, inspect, record against, or close a cumulative disclosure budget with total, per-recipient, and per-category limits. Stores hashes and counters, not disclosed content or recipient identities. Subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
manage_resource_leaseAtomically acquire, inspect, or release a short-lived exclusive lease on a hashed resource key.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.
Description, as the server wrote it Atomically acquire, inspect, or release a short-lived exclusive lease on a hashed resource key. Production; subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
manage_task_contractOffer, accept, inspect, complete, or cancel a digest-bound technical task commitment.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.
Description, as the server wrote it Offer, accept, inspect, complete, or cancel a digest-bound technical task commitment. This records service state; it is not a legal contract, escrow, payment, or identity verification. Production.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
manage_task_deadlineCreate, inspect, complete, or cancel a task deadline whose due and escalation state is derived from an independent server clock even when the agent is offline.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Create, inspect, complete, or cancel a task deadline whose due and escalation state is derived from an independent server clock even when the agent is offline. Subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
manage_task_handoffCreate a bearer-token task handoff, let another paid API identity claim it exactly once, and inspect, complete, or cancel the transfer.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Create a bearer-token task handoff, let another paid API identity claim it exactly once, and inspect, complete, or cancel the transfer. Only task fingerprints are stored. Production.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
manage_terms_pinPin, inspect, or revoke an immutable digest-bound record of observed terms, interface, version, and price.No findings
Why it is in this group
- The name "manage_terms_pin" says "pin": a word for a change.
Description, as the server wrote it Pin, inspect, or revoke an immutable digest-bound record of observed terms, interface, version, and price. Stores bounded metadata and digests, not the terms body. This is technical evidence, not a legal agreement. Subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
match_policy_requirementsDeterministically compare bounded provider capabilities with consumer-required and forbidden policy tokens.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 Deterministically compare bounded provider capabilities with consumer-required and forbidden policy tokens. Processes supplied tokens without storing policy content and does not make legal or compliance conclusions. Subscription API key required.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
prepare_for_agentUse as the default preprocessing step before an AI agent consumes untrusted external text.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 Use as the default preprocessing step before an AI agent consumes untrusted external text. Returns agent-ready text plus inspection, risk-scan, and secret-detection reports. Trial, subscription, or x402 pay-per-call.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
record_action_receiptCreate or retrieve an immutable receipt digest for an action outcome without storing the action or outcome payload.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Create or retrieve an immutable receipt digest for an action outcome without storing the action or outcome payload. Production; subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
record_quality_observationSubmit an opt-in structured observation for an exact target and task.1 finding
Why it is in this group
- The description's first verb is "submit": a word for a change.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...ons are E0. Stores no prompt, response, credential, email, or free-form review. Free verif..."
Description, as the server wrote it Submit an opt-in structured observation for an exact target and task. Receipt-linked observations are labeled E1; other observations are E0. Stores no prompt, response, credential, email, or free-form review. Free verified contributor or subscription key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
redact_sensitive_textUse before storing, sharing, logging, or sending text downstream when it may contain credentials or identifiers.1 finding
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.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...ing text downstream when it may contain credentials or identifiers. Pattern-based redaction..."
Description, as the server wrote it Use before storing, sharing, logging, or sending text downstream when it may contain credentials or identifiers. Pattern-based redaction; trial, subscription, or x402 pay-per-call.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
request_approvalUse when an agent needs independent human approval before a consequential action.No findings
Why it is in this group
- The name "request_approval" says "request": a word for a change.
Description, as the server wrote it Use when an agent needs independent human approval before a consequential action. Creates a secure approval link. Subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
request_quality_correctionAttach a digest-only correction or appeal request to a quality card.No findings
Why it is in this group
- The name "request_quality_correction" says "request": a word for a change.
Description, as the server wrote it Attach a digest-only correction or appeal request to a quality card. Requests are visible as unverified pending state and do not erase evidence or prove provider identity. Free verified contributor or subscription key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
reserve_action_budgetAtomically reserve integer units under a named, period-scoped ceiling.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.
Description, as the server wrote it Atomically reserve integer units under a named, period-scoped ceiling. A reservation_key makes retries idempotent. The service stores hashes and counters, not purchase details. Production; subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
rework_textUse when an agent needs a deterministic, no-LLM rewrite while preserving protected facts such as numbers, URLs, emails, and quotes.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 Use when an agent needs a deterministic, no-LLM rewrite while preserving protected facts such as numbers, URLs, emails, and quotes. Returns change metrics and preservation checks; does not verify authorship or watermark status. Trial, subscription, or x402 pay-per-call.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
sanitize_agent_contextUse before putting untrusted retrieved or uploaded text into a model context.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 Use before putting untrusted retrieved or uploaded text into a model context. Normalizes structural artifacts, returns risk signals, and can redact sensitive patterns. Trial, subscription, or x402 pay-per-call.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
scan_untrusted_textUse before an agent ingests pasted, retrieved, uploaded, or externally supplied text.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 Use before an agent ingests pasted, retrieved, uploaded, or externally supplied text. Returns structural and heuristic risk signals; it does not determine maliciousness or safety. Trial, subscription, or x402 pay-per-call.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
scrub_textNormalize hidden/control characters and formatting artifacts without rewriting wording.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 Normalize hidden/control characters and formatting artifacts without rewriting wording. Free or paid.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
verify_signed_signalVerify an HMAC-SHA256 signal, enforce timestamp freshness, and reject a replayed nonce.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.
Description, as the server wrote it Verify an HMAC-SHA256 signal, enforce timestamp freshness, and reject a replayed nonce. The message and shared secret are never stored. Production; subscription API key required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
Only reads 8Show 8 read-only tools
check_actionUse to inspect an idempotency key before or after an agent action.No findings
Why it is in this group
- The description's first verb is "inspect": a word for reading.
Description, as the server wrote it Use to inspect an idempotency key before or after an agent action. Subscription API key required.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
compare_quality_targetsReturn contextual quality cards for two to ten exact targets in caller-provided order.No findings
Why it is in this group
- The name "compare_quality_targets" says "compare": a word for reading.
Description, as the server wrote it Return contextual quality cards for two to ten exact targets in caller-provided order. It exposes evidence and uncertainty without producing a paid ranking or universal winner. Free.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
compare_textUse to verify what changed between two text versions and whether differences are only scrub/format artifacts.No findings
Why it is in this group
- The name "compare_text" says "compare": a word for reading.
Description, as the server wrote it Use to verify what changed between two text versions and whether differences are only scrub/format artifacts. Trial, subscription, or x402 pay-per-call.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_quality_cardRetrieve a public, contextual quality card for an exact MCP server or REST API version.No findings
Why it is in this group
- The name "get_quality_card" says "get": a word for reading.
Description, as the server wrote it Retrieve a public, contextual quality card for an exact MCP server or REST API version. Scores remain unavailable until at least three independent verified contributors submit structured observations. Free.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_signal_eventsPaid: retrieve events received by a temporary signal inbox in arrival order.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_signal_events" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "inbox": it reads mail.
- private-dataThe input names an inbox (input.inbox_id), and the tool reads: it reads mail.
- untrusted-inputThe description's first sentence says "inbox": it reads inbound email, which other people can write.
Description, as the server wrote it Paid: retrieve events received by a temporary signal inbox in arrival order.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
inspect_textInspect exact Unicode, invisible characters, normalization, and mixed-script anomalies.No findings
Why it is in this group
- The name "inspect_text" says "inspect": a word for reading.
Description, as the server wrote it Inspect exact Unicode, invisible characters, normalization, and mixed-script anomalies. Free or paid.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_quality_cardsList exact service-version/task quality cards that have reached the public three-verified-contributor evidence threshold.No findings
Why it is in this group
- The name "list_quality_cards" says "list": a word for reading.
Description, as the server wrote it List exact service-version/task quality cards that have reached the public three-verified-contributor evidence threshold. Results are ordered by recent evidence, not quality, payment, or sponsorship. Free.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
validate_outputUse immediately before a downstream action when model output must be valid JSON or match a schema.No findings
Why it is in this group
- The name "validate_output" says "validate": a word for reading.
Description, as the server wrote it Use immediately before a downstream action when model output must be valid JSON or match a schema. Trial, subscription, or x402 pay-per-call.
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 outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- 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, 18:46 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
- 41
- Protocol version
- 2025-11-25
- 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 41 tools that change things (3 destructive, 1 irreversible, 37 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.scrubmytext.com/mcp: tools/list returned 49 tools to an anonymous client, including release_action (destructive), delete_signal (destructive), cancel_approval (destructive), manage_context_status (irreversible), scrub_text (write) and 36 more
Findings
Matches of fixed checks, with the text they matched.
The description mentions "credentials".
What this check looks forMatched text
description: "...ing text downstream when it may contain credentials or identifiers. Pattern-based redaction..."
- Infodetect_secrets
The description mentions "credentials".
What this check looks forMatched text
description: "...ores, or forwards text that may contain credentials. Finds likely API keys, private keys, J..."
The description mentions "credential".
What this check looks forMatched text
description: "...ons are E0. Stores no prompt, response, credential, email, or free-form review. Free verif..."
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 7.5.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http tools https://api.scrubmytext.com/mcpclaude mcp add --transport http tools https://api.scrubmytext.com/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__tools__inspect_text",
"mcp__tools__compare_text",
"mcp__tools__validate_output",
"mcp__tools__check_action",
"mcp__tools__get_signal_events",
"mcp__tools__list_quality_cards",
"mcp__tools__get_quality_card",
"mcp__tools__compare_quality_targets"
],
"ask": [
"mcp__tools__scrub_text",
"mcp__tools__scan_untrusted_text",
"mcp__tools__redact_sensitive_text",
"mcp__tools__detect_secrets",
"mcp__tools__sanitize_agent_context",
"mcp__tools__prepare_for_agent",
"mcp__tools__rework_text",
"mcp__tools__fingerprint_action",
"mcp__tools__lock_action",
"mcp__tools__lock_action_intent",
"mcp__tools__complete_action",
"mcp__tools__create_signal",
"mcp__tools__request_approval",
"mcp__tools__check_approval",
"mcp__tools__manage_action_challenge",
"mcp__tools__reserve_action_budget",
"mcp__tools__record_action_receipt",
"mcp__tools__verify_signed_signal",
"mcp__tools__manage_resource_lease",
"mcp__tools__manage_authority_delegation",
"mcp__tools__manage_agent_stop",
"mcp__tools__manage_task_handoff",
"mcp__tools__manage_action_reconciliation",
"mcp__tools__anchor_context_trace",
"mcp__tools__manage_task_contract",
"mcp__tools__check_agent_readiness",
"mcp__tools__manage_action_quorum",
"mcp__tools__manage_task_deadline",
"mcp__tools__manage_attention_budget",
"mcp__tools__manage_agent_escalation",
"mcp__tools__manage_terms_pin",
"mcp__tools__match_policy_requirements",
"mcp__tools__manage_action_compensation",
"mcp__tools__manage_context_status",
"mcp__tools__manage_context_rights",
"mcp__tools__manage_disclosure_budget",
"mcp__tools__record_quality_observation",
"mcp__tools__request_quality_correction"
],
"deny": [
"mcp__tools__release_action",
"mcp__tools__delete_signal",
"mcp__tools__cancel_approval"
]
}
}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 tools. Review it before you use it.
Capability tags behind 1 rule
- mcp__tools__get_signal_events private-data, 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/com.scrubmytext/tools/verify?hash=fff6dd504fd1a08444d308e4ad022027ee6f03a0fe012d214c5544ad01c989da" | jq -e '.changed == false'Pinned hash fff6dd504fd1, from Nov 14, 2026, 07:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.scrubmytext/tools/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.scrubmytext/tools)Source: MCP Registry. Synced Oct 21, 2026, 18:04 UTC.
ScrubMyText + Agent Infrastructure MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ScrubMyText + Agent Infrastructure MCP server safe?
- No scan can promise that. What its definitions show: 49 tools, 41 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 ScrubMyText + Agent Infrastructure MCP server delete data?
- Yes. 3 tools can delete, cancel or revoke something: release_action, delete_signal and cancel_approval.
Can the ScrubMyText + Agent Infrastructure MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: manage_context_status.
What tools does the ScrubMyText + Agent Infrastructure MCP server have?
- 49 tools: 3 destructive, 1 irreversible, 37 write, 8 read. release_action, delete_signal, cancel_approval, manage_context_status, scrub_text, scan_untrusted_text, redact_sensitive_text, detect_secrets and 41 more.
Does the ScrubMyText + Agent Infrastructure MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the ScrubMyText + Agent Infrastructure MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the ScrubMyText + Agent Infrastructure MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 14, 2026.