{"name":"io.github.BlackFoil/claude-token-saver-mcp","slug":"blackfoil-claude-token-saver-mcp","title":null,"description":"MCP server that offloads routine coding tasks to local LLM (Ollama) to save Claude API tokens","url":"https://mcp.market/server/blackfoil-claude-token-saver-mcp","rating":null,"grade":"B","score":75,"certified":false,"status":"active","category":"ai","tags":["ai"],"presence":{"score":19,"stars":4,"forks":0,"downloads_week":63,"last_push_at":"2026-03-31T09:23:09.000Z","license":"Apache-2.0"},"uptime":null,"claimed":false,"transport":"npm","callable_via_gateway":false,"default_price_micros":0,"repository":"https://github.com/BlackFoil/claude-token-saver-mcp","website":null,"version":"0.3.2","remotes":[],"packages":[{"registryType":"npm","identifier":"claude-token-saver-mcp","version":"0.3.2","transport":{"type":"stdio"}}],"tools":[{"name":"auto_setup","description":"Automate the full model setup flow: recommend the best model for a task category, download it if needed, and preload it into VRAM \\u2014 all in one step.","write_action":false,"price_micros":0,"input_schema":null},{"name":"batch_offload","description":"Submit multiple coding tasks as a batch to the local LLM. Tasks are processed sequentially or in parallel. Supports partial failure.","write_action":true,"price_micros":0,"input_schema":null},{"name":"compress_context","description":"Compress/summarize large text content using a local LLM to reduce cloud token usage. Use for summarizing logs, large files, or verbose context before sending to Claude.","write_action":false,"price_micros":0,"input_schema":null},{"name":"configure_model_selector","description":"View or modify model selector settings at runtime. Manage blocked models, license filters, and custom model recommendations.","write_action":false,"price_micros":0,"input_schema":null},{"name":"cost_dashboard","description":"View cumulative cost savings and model usage statistics.","write_action":false,"price_micros":0,"input_schema":null},{"name":"get_metrics","description":"Get server metrics in Prometheus text format or JSON. Includes request counts, latency, queue stats, cost savings, and health status.","write_action":false,"price_micros":0,"input_schema":null},{"name":"list_loaded_models","description":"List all models currently loaded in VRAM with usage details. Shows VRAM usage, expiry time, and available slots.","write_action":false,"price_micros":0,"input_schema":null},{"name":"offload_work","description":"Offload coding/text tasks to a local LLM (Ollama) to save Claude API tokens. Use for code generation, refactoring, formatting, boilerplate, and other routine tasks.","write_action":false,"price_micros":0,"input_schema":null},{"name":"preload_model","description":"Preload a model into VRAM for warm inference. Sends an empty chat request with keep_alive to keep the model loaded during the session.","write_action":false,"price_micros":0,"input_schema":null},{"name":"pull_model","description":"Download a model from the Ollama registry to local storage. Use this to install recommended models before preloading them into VRAM.","write_action":false,"price_micros":0,"input_schema":null},{"name":"recommend_model","description":"Recommend the best local LLM model for a given task category based on system specs and installed models. Returns prioritized list with installation status and license info.","write_action":false,"price_micros":0,"input_schema":null}],"scan":{"score":75,"grade":"B","scanned_at":"2026-09-27T23:18:43.490Z","report":{"scannerVersion":"0.1.9","scannedAt":"2026-09-27T23:18:43.396Z","components":{"code":{"score":25,"max":25,"notes":["3 source files scanned"]},"reliability":{"score":-1,"max":20,"notes":["no gateway calls yet and no remote to probe"]},"poisoning":{"score":-1,"max":15,"notes":["tools not inspected (local package is not executed); not counted"]},"auth":{"score":12,"max":15,"notes":["local package, no credentials required"]},"maintenance":{"score":4,"max":15,"notes":["last push 181 days ago"]},"identity":{"score":8,"max":10,"notes":["registry namespace matches repository owner","GitHub account older than a year"]}},"findings":[],"inputs":{"packages":[{"registryType":"npm","identifier":"claude-token-saver-mcp","version":"0.3.2","found":true,"license":"Apache-2.0","hasInstallScripts":false,"dependencyCount":3,"publishedAt":"2026-03-31T09:23:02.594Z","repositoryUrl":"git+https://github.com/BlackFoil/claude-token-saver-mcp.git","weeklyDownloads":63}],"repo":{"found":true,"owner":"BlackFoil","repo":"claude-token-saver-mcp","archived":false,"pushedAt":"2026-03-31T09:23:09Z","stars":4,"forks":0,"openIssues":0,"ownerType":"User","ownerAvatarUrl":"https://avatars.githubusercontent.com/u/127078112?v=4","ownerCreatedAt":"2023-03-06T05:39:20Z","license":"Apache-2.0"},"icon":{"url":"https://avatars.githubusercontent.com/u/127078112?v=4&s=128","source":"github"},"presence":{"stars":4,"forks":0,"downloadsWeek":63,"license":"Apache-2.0","lastPushAt":"2026-03-31T09:23:09.000Z","score":19}}}},"grade_history":[],"reviews":[]}