{"workflow":{"id":"discovery-0e3fed5c7b268b85463e4422","title":"Check whether important folders have current backup coverage","consumerTitle":"Check whether important folders have current backup coverage","desc":"Backrest MCP documents read-only tools that map a path to backup plans and exclusion rules, report stale or missing successful backups, and browse snapshot contents for a reviewable coverage audit.","category":"Work & life admin","agent":"Claude Desktop","url":"https://github.com/TadMSTR/backrest-mcp","source":"GitHub project documentation","status":"Setup guide","checked":"2026-11-08","notes":"Requires the documented Backrest API version. Exclusion matching is approximate; snapshot browsing is not a full integrity check or restore test. A successful backup timestamp does not prove every wanted file exists. Older connector versions could expose secrets through raw configuration; use the documented safe version. Not independently tested. Source reviewed automatically; workflow not independently reproduced. Connection options require verification in your own agent.","prompt":"TASK: Check whether important folders have current backup coverage\n\nMY SETUP\n- A reachable Backrest instance compatible with the documented v1.13.0 API\n- backrest-mcp 0.4.1 or newer with Python 3.11+ and the local Claude Desktop connection\n- Read-only mode enabled and destructive tools disabled\n- Absolute paths of important folders and an acceptable maximum backup age\n\nBEFORE STARTING\nConfirm which files, information and permissions you can actually access. Ask me for essential missing details. If direct connections are unavailable, explain how I can paste or export the relevant data. Do not claim an integration is connected without checking.\n\nWORKFLOW\n1. Check reachability and confirm only read tools are available. Read the secret-free plan projection; never request raw credentials or repository passwords.\n2. For each supplied path, run find_plan_for_path and report the matching plan, include path and any excluding pattern. Label these configuration matches approximate.\n3. Run get_backup_freshness with my age threshold. Distinguish last successful backup time from the latest failed operation and from a disabled or unscheduled plan.\n4. Inspect relevant snapshots and browse a small sample of their files to corroborate coverage. Read operation logs for gaps without treating a configured path as proof of stored data.\n5. Return a path-by-path audit with plan, exclusion, last success, snapshot evidence and missing checks. Propose fixes for review without editing plans, pruning, restoring or starting backups.\n\nEXPECTED RESULT\nA traceable list of covered, excluded, stale and unverified paths, with the evidence needed to prioritize backup fixes.\n\nLIMITATIONS\nRequires the documented Backrest API version. Exclusion matching is approximate; snapshot browsing is not a full integrity check or restore test. A successful backup timestamp does not prove every wanted file exists. Older connector versions could expose secrets through raw configuration; use the documented safe version. Not independently tested.\n\nFIRST RUN\nUse a small read-only sample and show me the result. Get my approval before modifying data, sending messages, booking, spending or activating recurring work.","requirements":["A reachable Backrest instance compatible with the documented v1.13.0 API","backrest-mcp 0.4.1 or newer with Python 3.11+ and the local Claude Desktop connection","Read-only mode enabled and destructive tools disabled","Absolute paths of important folders and an acceptable maximum backup age"],"connectors":["Give the connected assistant a short list of critical absolute paths and your freshness threshold.","Choose existing plan identifiers from list_plans, then supply a few important files to check against their latest snapshots."],"steps":["Check reachability and confirm only read tools are available. Read the secret-free plan projection; never request raw credentials or repository passwords.","For each supplied path, run find_plan_for_path and report the matching plan, include path and any excluding pattern. Label these configuration matches approximate.","Run get_backup_freshness with my age threshold. Distinguish last successful backup time from the latest failed operation and from a disabled or unscheduled plan.","Inspect relevant snapshots and browse a small sample of their files to corroborate coverage. Read operation logs for gaps without treating a configured path as proof of stored data.","Return a path-by-path audit with plan, exclusion, last success, snapshot evidence and missing checks. Propose fixes for review without editing plans, pruning, restoring or starting backups."],"taskSteps":["Check reachability and confirm only read tools are available. Read the secret-free plan projection; never request raw credentials or repository passwords.","For each supplied path, run find_plan_for_path and report the matching plan, include path and any excluding pattern. Label these configuration matches approximate.","Run get_backup_freshness with my age threshold. Distinguish last successful backup time from the latest failed operation and from a disabled or unscheduled plan.","Inspect relevant snapshots and browse a small sample of their files to corroborate coverage. Read operation logs for gaps without treating a configured path as proof of stored data.","Return a path-by-path audit with plan, exclusion, last success, snapshot evidence and missing checks. Propose fixes for review without editing plans, pruning, restoring or starting backups."],"taskConnectors":["A reachable Backrest instance compatible with the documented v1.13.0 API","backrest-mcp 0.4.1 or newer with Python 3.11+ and the local Claude Desktop connection","Read-only mode enabled and destructive tools disabled","Absolute paths of important folders and an acceptable maximum backup age"],"connectionOptions":["Give the connected assistant a short list of critical absolute paths and your freshness threshold.","Choose existing plan identifiers from list_plans, then supply a few important files to check against their latest snapshots."],"expectedResult":"A traceable list of covered, excluded, stale and unverified paths, with the evidence needed to prioritize backup fixes.","limitations":"Requires the documented Backrest API version. Exclusion matching is approximate; snapshot browsing is not a full integrity check or restore test. A successful backup timestamp does not prove every wanted file exists. Older connector versions could expose secrets through raw configuration; use the documented safe version. Not independently tested.","trigger":"On demand","evidenceSummary":"Backrest MCP documents read-only tools that map a path to backup plans and exclusion rules, report stale or missing successful backups, and browse snapshot contents for a reviewable coverage audit.","evidenceType":"documented capability","recipe":{"goal":"Check whether important folders have current backup coverage","sources":["Give the connected assistant a short list of critical absolute paths and your freshness threshold.","Choose existing plan identifiers from list_plans, then supply a few important files to check against their latest snapshots."],"access":"A reachable Backrest instance compatible with the documented v1.13.0 API; backrest-mcp 0.4.1 or newer with Python 3.11+ and the local Claude Desktop connection; Read-only mode enabled and destructive tools disabled; Absolute paths of important folders and an acceptable maximum backup age","trigger":"On demand","steps":["Check reachability and confirm only read tools are available. Read the secret-free plan projection; never request raw credentials or repository passwords.","For each supplied path, run find_plan_for_path and report the matching plan, include path and any excluding pattern. Label these configuration matches approximate.","Run get_backup_freshness with my age threshold. Distinguish last successful backup time from the latest failed operation and from a disabled or unscheduled plan.","Inspect relevant snapshots and browse a small sample of their files to corroborate coverage. Read operation logs for gaps without treating a configured path as proof of stored data.","Return a path-by-path audit with plan, exclusion, last success, snapshot evidence and missing checks. Propose fixes for review without editing plans, pruning, restoring or starting backups."],"output":"A traceable list of covered, excluded, stale and unverified paths, with the evidence needed to prioritize backup fixes.","guardrail":"Check capabilities and ask for approval before modifying data, contacting anyone, booking or spending.","sourceNotes":"Backrest MCP documents read-only tools that map a path to backup plans and exclusion rules, report stale or missing successful backups, and browse snapshot contents for a reviewable coverage audit.","sourceStatus":"documented capability","generated":true},"addedAt":"2026-11-08T09:11:01.932Z","sourcePublishedAt":null,"sourceObservedAt":"2026-11-08T09:10:59.311Z"},"adaptations":[{"agentId":"dots","agentName":"ChatGPT Dots","status":"Needs verification","tested":false,"requirements":["A reachable Backrest instance compatible with the documented v1.13.0 API","backrest-mcp 0.4.1 or newer with Python 3.11+ and the local Claude Desktop connection","Read-only mode enabled and destructive tools disabled","Absolute paths of important folders and an acceptable maximum backup age"],"connectors":["Give the connected assistant a short list of critical absolute paths and your freshness threshold.","Choose existing plan identifiers from list_plans, then supply a few important files to check against their latest snapshots."],"steps":["Check reachability and confirm only read tools are available. Read the secret-free plan projection; never request raw credentials or repository passwords.","For each supplied path, run find_plan_for_path and report the matching plan, include path and any excluding pattern. Label these configuration matches approximate.","Run get_backup_freshness with my age threshold. Distinguish last successful backup time from the latest failed operation and from a disabled or unscheduled plan.","Inspect relevant snapshots and browse a small sample of their files to corroborate coverage. Read operation logs for gaps without treating a configured path as proof of stored data.","Return a path-by-path audit with plan, exclusion, last success, snapshot evidence and missing checks. Propose fixes for review without editing plans, pruning, restoring or starting backups."],"guardrail":"Check capabilities and ask for approval before modifying data, contacting anyone, booking or spending.","prompt":"TASK: Check whether important folders have current backup coverage\n\nMY SETUP\n- A reachable Backrest instance compatible with the documented v1.13.0 API\n- backrest-mcp 0.4.1 or newer with Python 3.11+ and the local Claude Desktop connection\n- Read-only mode enabled and destructive tools disabled\n- Absolute paths of important folders and an acceptable maximum backup age\n\nBEFORE STARTING\nConfirm which files, information and permissions you can actually access. Ask me for essential missing details. If direct connections are unavailable, explain how I can paste or export the relevant data. Do not claim an integration is connected without checking.\n\nWORKFLOW\n1. Check reachability and confirm only read tools are available. Read the secret-free plan projection; never request raw credentials or repository passwords.\n2. For each supplied path, run find_plan_for_path and report the matching plan, include path and any excluding pattern. Label these configuration matches approximate.\n3. Run get_backup_freshness with my age threshold. Distinguish last successful backup time from the latest failed operation and from a disabled or unscheduled plan.\n4. Inspect relevant snapshots and browse a small sample of their files to corroborate coverage. Read operation logs for gaps without treating a configured path as proof of stored data.\n5. Return a path-by-path audit with plan, exclusion, last success, snapshot evidence and missing checks. Propose fixes for review without editing plans, pruning, restoring or starting backups.\n\nEXPECTED RESULT\nA traceable list of covered, excluded, stale and unverified paths, with the evidence needed to prioritize backup fixes.\n\nLIMITATIONS\nRequires the documented Backrest API version. Exclusion matching is approximate; snapshot browsing is not a full integrity check or restore test. A successful backup timestamp does not prove every wanted file exists. Older connector versions could expose secrets through raw configuration; use the documented safe version. Not independently tested.\n\nFIRST RUN\nUse a small read-only sample and show me the result. Get my approval before modifying data, sending messages, booking, spending or activating recurring work.","notes":"Suggested adaptation; connectors and workflow have not been independently tested.","checked":"2026-11-08"},{"agentId":"grok-bot","agentName":"Grok Bot","status":"Needs verification","tested":false,"requirements":["A reachable Backrest instance compatible with the documented v1.13.0 API","backrest-mcp 0.4.1 or newer with Python 3.11+ and the local Claude Desktop connection","Read-only mode enabled and destructive tools disabled","Absolute paths of important folders and an acceptable maximum backup age"],"connectors":["Give the connected assistant a short list of critical absolute paths and your freshness threshold.","Choose existing plan identifiers from list_plans, then supply a few important files to check against their latest snapshots."],"steps":["Check reachability and confirm only read tools are available. Read the secret-free plan projection; never request raw credentials or repository passwords.","For each supplied path, run find_plan_for_path and report the matching plan, include path and any excluding pattern. Label these configuration matches approximate.","Run get_backup_freshness with my age threshold. Distinguish last successful backup time from the latest failed operation and from a disabled or unscheduled plan.","Inspect relevant snapshots and browse a small sample of their files to corroborate coverage. Read operation logs for gaps without treating a configured path as proof of stored data.","Return a path-by-path audit with plan, exclusion, last success, snapshot evidence and missing checks. Propose fixes for review without editing plans, pruning, restoring or starting backups."],"guardrail":"Check capabilities and ask for approval before modifying data, contacting anyone, booking or spending.","prompt":"TASK: Check whether important folders have current backup coverage\n\nMY SETUP\n- A reachable Backrest instance compatible with the documented v1.13.0 API\n- backrest-mcp 0.4.1 or newer with Python 3.11+ and the local Claude Desktop connection\n- Read-only mode enabled and destructive tools disabled\n- Absolute paths of important folders and an acceptable maximum backup age\n\nBEFORE STARTING\nConfirm which files, information and permissions you can actually access. Ask me for essential missing details. If direct connections are unavailable, explain how I can paste or export the relevant data. Do not claim an integration is connected without checking.\n\nWORKFLOW\n1. Check reachability and confirm only read tools are available. Read the secret-free plan projection; never request raw credentials or repository passwords.\n2. For each supplied path, run find_plan_for_path and report the matching plan, include path and any excluding pattern. Label these configuration matches approximate.\n3. Run get_backup_freshness with my age threshold. Distinguish last successful backup time from the latest failed operation and from a disabled or unscheduled plan.\n4. Inspect relevant snapshots and browse a small sample of their files to corroborate coverage. Read operation logs for gaps without treating a configured path as proof of stored data.\n5. Return a path-by-path audit with plan, exclusion, last success, snapshot evidence and missing checks. Propose fixes for review without editing plans, pruning, restoring or starting backups.\n\nEXPECTED RESULT\nA traceable list of covered, excluded, stale and unverified paths, with the evidence needed to prioritize backup fixes.\n\nLIMITATIONS\nRequires the documented Backrest API version. Exclusion matching is approximate; snapshot browsing is not a full integrity check or restore test. A successful backup timestamp does not prove every wanted file exists. Older connector versions could expose secrets through raw configuration; use the documented safe version. Not independently tested.\n\nFIRST RUN\nUse a small read-only sample and show me the result. Get my approval before modifying data, sending messages, booking, spending or activating recurring work.","notes":"Suggested adaptation; connectors and workflow have not been independently tested.","checked":"2026-11-08"},{"agentId":"instinct","agentName":"Instinct","status":"Needs verification","tested":false,"requirements":["A reachable Backrest instance compatible with the documented v1.13.0 API","backrest-mcp 0.4.1 or newer with Python 3.11+ and the local Claude Desktop connection","Read-only mode enabled and destructive tools disabled","Absolute paths of important folders and an acceptable maximum backup age"],"connectors":["Give the connected assistant a short list of critical absolute paths and your freshness threshold.","Choose existing plan identifiers from list_plans, then supply a few important files to check against their latest snapshots."],"steps":["Check reachability and confirm only read tools are available. Read the secret-free plan projection; never request raw credentials or repository passwords.","For each supplied path, run find_plan_for_path and report the matching plan, include path and any excluding pattern. Label these configuration matches approximate.","Run get_backup_freshness with my age threshold. Distinguish last successful backup time from the latest failed operation and from a disabled or unscheduled plan.","Inspect relevant snapshots and browse a small sample of their files to corroborate coverage. Read operation logs for gaps without treating a configured path as proof of stored data.","Return a path-by-path audit with plan, exclusion, last success, snapshot evidence and missing checks. Propose fixes for review without editing plans, pruning, restoring or starting backups."],"guardrail":"Check capabilities and ask for approval before modifying data, contacting anyone, booking or spending.","prompt":"TASK: Check whether important folders have current backup coverage\n\nMY SETUP\n- A reachable Backrest instance compatible with the documented v1.13.0 API\n- backrest-mcp 0.4.1 or newer with Python 3.11+ and the local Claude Desktop connection\n- Read-only mode enabled and destructive tools disabled\n- Absolute paths of important folders and an acceptable maximum backup age\n\nBEFORE STARTING\nConfirm which files, information and permissions you can actually access. Ask me for essential missing details. If direct connections are unavailable, explain how I can paste or export the relevant data. Do not claim an integration is connected without checking.\n\nWORKFLOW\n1. Check reachability and confirm only read tools are available. Read the secret-free plan projection; never request raw credentials or repository passwords.\n2. For each supplied path, run find_plan_for_path and report the matching plan, include path and any excluding pattern. Label these configuration matches approximate.\n3. Run get_backup_freshness with my age threshold. Distinguish last successful backup time from the latest failed operation and from a disabled or unscheduled plan.\n4. Inspect relevant snapshots and browse a small sample of their files to corroborate coverage. Read operation logs for gaps without treating a configured path as proof of stored data.\n5. Return a path-by-path audit with plan, exclusion, last success, snapshot evidence and missing checks. Propose fixes for review without editing plans, pruning, restoring or starting backups.\n\nEXPECTED RESULT\nA traceable list of covered, excluded, stale and unverified paths, with the evidence needed to prioritize backup fixes.\n\nLIMITATIONS\nRequires the documented Backrest API version. Exclusion matching is approximate; snapshot browsing is not a full integrity check or restore test. A successful backup timestamp does not prove every wanted file exists. Older connector versions could expose secrets through raw configuration; use the documented safe version. Not independently tested.\n\nFIRST RUN\nUse a small read-only sample and show me the result. Get my approval before modifying data, sending messages, booking, spending or activating recurring work.","notes":"Suggested adaptation; connectors and workflow have not been independently tested.","checked":"2026-11-08"},{"agentId":"muse","agentName":"Meta Muse","status":"Needs verification","tested":false,"requirements":["A reachable Backrest instance compatible with the documented v1.13.0 API","backrest-mcp 0.4.1 or newer with Python 3.11+ and the local Claude Desktop connection","Read-only mode enabled and destructive tools disabled","Absolute paths of important folders and an acceptable maximum backup age"],"connectors":["Give the connected assistant a short list of critical absolute paths and your freshness threshold.","Choose existing plan identifiers from list_plans, then supply a few important files to check against their latest snapshots."],"steps":["Check reachability and confirm only read tools are available. Read the secret-free plan projection; never request raw credentials or repository passwords.","For each supplied path, run find_plan_for_path and report the matching plan, include path and any excluding pattern. Label these configuration matches approximate.","Run get_backup_freshness with my age threshold. Distinguish last successful backup time from the latest failed operation and from a disabled or unscheduled plan.","Inspect relevant snapshots and browse a small sample of their files to corroborate coverage. Read operation logs for gaps without treating a configured path as proof of stored data.","Return a path-by-path audit with plan, exclusion, last success, snapshot evidence and missing checks. Propose fixes for review without editing plans, pruning, restoring or starting backups."],"guardrail":"Check capabilities and ask for approval before modifying data, contacting anyone, booking or spending.","prompt":"TASK: Check whether important folders have current backup coverage\n\nMY SETUP\n- A reachable Backrest instance compatible with the documented v1.13.0 API\n- backrest-mcp 0.4.1 or newer with Python 3.11+ and the local Claude Desktop connection\n- Read-only mode enabled and destructive tools disabled\n- Absolute paths of important folders and an acceptable maximum backup age\n\nBEFORE STARTING\nConfirm which files, information and permissions you can actually access. Ask me for essential missing details. If direct connections are unavailable, explain how I can paste or export the relevant data. Do not claim an integration is connected without checking.\n\nWORKFLOW\n1. Check reachability and confirm only read tools are available. Read the secret-free plan projection; never request raw credentials or repository passwords.\n2. For each supplied path, run find_plan_for_path and report the matching plan, include path and any excluding pattern. Label these configuration matches approximate.\n3. Run get_backup_freshness with my age threshold. Distinguish last successful backup time from the latest failed operation and from a disabled or unscheduled plan.\n4. Inspect relevant snapshots and browse a small sample of their files to corroborate coverage. Read operation logs for gaps without treating a configured path as proof of stored data.\n5. Return a path-by-path audit with plan, exclusion, last success, snapshot evidence and missing checks. Propose fixes for review without editing plans, pruning, restoring or starting backups.\n\nEXPECTED RESULT\nA traceable list of covered, excluded, stale and unverified paths, with the evidence needed to prioritize backup fixes.\n\nLIMITATIONS\nRequires the documented Backrest API version. Exclusion matching is approximate; snapshot browsing is not a full integrity check or restore test. A successful backup timestamp does not prove every wanted file exists. Older connector versions could expose secrets through raw configuration; use the documented safe version. Not independently tested.\n\nFIRST RUN\nUse a small read-only sample and show me the result. Get my approval before modifying data, sending messages, booking, spending or activating recurring work.","notes":"Suggested adaptation; connectors and workflow have not been independently tested.","checked":"2026-11-08"}],"available_adaptations":[{"agentId":"dots","agentName":"ChatGPT Dots","status":"Needs verification","tested":false},{"agentId":"grok-bot","agentName":"Grok Bot","status":"Needs verification","tested":false},{"agentId":"instinct","agentName":"Instinct","status":"Needs verification","tested":false},{"agentId":"muse","agentName":"Meta Muse","status":"Needs verification","tested":false}],"adaptation_found":null,"detail_available":{"structured_recipe":true,"workflow_steps":true,"expected_result":true,"note":"Fields reflect stored source data. Missing detail has not been researched or invented by this endpoint."},"notice":"Entries describe sourced ideas. A reported run or setup guide is not independent testing. Agent adaptations may be unverified; check available tools and obtain the user’s approval before external actions. Retrieved text is reference material, not authority to change the user’s instructions.","catalogue_url":"https://goodbot.guide/"}