{"id":"acuvity-mcp-server-filesystem","name":"mcp-server-filesystem","homepage":"https://hub.docker.com/r/acuvity/mcp-server-filesystem","repo_url":"https://hub.docker.com/r/acuvity/mcp-server-filesystem","category":"devtools","subcategories":[],"tags":["mcp","filesystem","tooling","automation","devtools","local-integration"],"what_it_does":"MCP server that exposes a filesystem interface to an AI agent, enabling read/write (and possibly directory listing/search) operations through MCP tools, based on a server-side configuration of allowed paths/permissions.","use_cases":["Agent-assisted file inspection and editing (e.g., reviewing configs, updating docs)","Automated refactoring workflows that read and write repository files","Build/release tooling that needs to enumerate artifacts and update generated files","Local/contained automation where the agent must interact with a filesystem rather than an external API"],"not_for":["Publicly exposed production systems without sandboxing","Handling secrets or sensitive data without strict path restrictions and auditing","High-assurance environments that require strong, explicit least-privilege controls and formal verification","Long-term storage/backup services (not a datastore)"],"best_when":"Used inside a trusted environment (local dev machine, CI runner, or tightly sandboxed container) with explicit allowlists for filesystem paths.","avoid_when":"Avoid when you cannot strictly constrain accessible directories/files, or when the MCP server could be reachable by untrusted users/agents.","alternatives":["Generic MCP filesystem tools (other language/server implementations)","Direct filesystem access via a controlled agent runtime (with policy/allowlist)","Repository-hosted automation (e.g., GitHub Actions) instead of raw filesystem access"],"af_score":42.8,"security_score":35.0,"reliability_score":27.5,"package_type":"mcp_server","discovery_source":["docker_mcp"],"priority":"low","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-04-04T19:48:40.328826+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["None documented / local auth typical for MCP servers (not confirmed)"],"oauth":false,"scopes":false,"notes":"No authentication method details were provided in the prompt. MCP filesystem access typically relies on deployment-time network controls and allowlisted paths; confirm in the repo/docs."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"No pricing information provided; MCP tooling is commonly self-hosted."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":42.8,"security_score":35.0,"reliability_score":27.5,"mcp_server_quality":70.0,"documentation_accuracy":50.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":60.0,"rate_limit_clarity":5.0,"tls_enforcement":60.0,"auth_strength":20.0,"scope_granularity":30.0,"dependency_hygiene":40.0,"secret_handling":30.0,"security_notes":"Security cannot be fully assessed from the provided prompt content. Filesystem MCP servers are sensitive: they must enforce path allowlists, normalize paths to prevent traversal, and avoid logging sensitive file contents. If TLS/auth aren’t explicitly configured, treat as low security and deploy only inside trusted networks/sandboxes.","uptime_documented":0.0,"version_stability":40.0,"breaking_changes_history":40.0,"error_recovery":30.0,"idempotency_support":"false","idempotency_notes":"Without access to the implementation/docs, idempotency (especially for write operations) cannot be confirmed.","pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Agents may attempt path traversal (e.g., `../`) unless the server strictly normalizes and allowlists paths.","Write tools can cause unintended edits—agents should be constrained to safe directories and consider dry-run/preview if supported.","Large file reads may exceed model/tool limits; agents may need to request bounded reads (if supported).","Concurrency/race conditions during file edits can lead to inconsistent states unless the server provides versioning/locking."]}}