# `com.moltlinestudio/research` on anlyon.dev > Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by anlyon.dev. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX]. > No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour. - Page: https://anlyon.dev/servers/com.moltlinestudio/research - JSON: https://anlyon.dev/api/v1/servers/com.moltlinestudio/research - Version: 1.2.0 (active) - Publisher: com.moltlinestudio (domain proven to the MCP Registry) - Runs: remote (streamable-http) - Sign-in to list tools: none - Repository: https://github.com/GarphenGate/moltline-mcp - Metadata from the official MCP Registry, synced 2026-10-21T17:59:33.306Z Title and description, as the publisher wrote them: ```untrusted-server-text Moltline Research Desk 7 research navigation, thesis, note-taking and citation skill products. 6 of 8 free. ``` Scanned 2026-10-21T19:13:36.358Z over streamable-http. **8 tools: 3 change things and 5 only read.** | Group | Class | Tools | Claude Code | | --- | --- | --- | --- | | Deletes or cancels | destructive | 0 | deny | | Can't be undone | irreversible | 0 | ask | | Changes things | write | 3 | ask | | Only reads | read | 5 | allow | ## Findings No check matched anything in these tool definitions. ## Changes things (3) Creates or changes something that can be changed back. Claude Code: ask. ### `confidence_interval` - 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: ```untrusted-server-text Compute a confidence interval for a mean (normal approximation). FREE. Typical input {"mean": 72.4, "std_dev": 8.1, "n": 64, "confidence_pct": 95} returns {"mean": 72.4, "margin_of_error": 1.9845, "interval": [70.4155, 74.3845], "note": "..."}. Use on data already collected, for a mean. Normal approximation, so it is unreliable on very small or heavily skewed samples. Not for proportions or two-group comparisons - the data server's ab_test compares two proportions. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""} (for example {"error": "confidence 90/95/99, n>=2, std_dev>=0"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry. ``` ### `format_citation` - 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: ```untrusted-server-text Format a citation in APA 7, MLA 9, or Chicago author-date style. FREE. Typical input {"style": "apa", "authors": ["Curie, Marie"], "year": 1911, "title": "Radium and radioactivity", "container": "Century Magazine"} returns {"style": "apa", "citation": "Curie, M. (1911). Radium and radioactivity. Century Magazine.", "note": "..."}. Use when the source details are already known and only the formatting is missing. Not for finding or verifying a source. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""} (for example {"error": "style must be apa, mla, or chicago"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry. ``` ### `sample_size` - 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: ```untrusted-server-text Calculate the survey sample size needed for a confidence level and margin. FREE. Uses maximum variance (p=0.5) with a finite-population correction when population is given. Typical input {"population": 5000, "confidence_pct": 95, "margin_pct": 5} returns {"required_sample": 357, "assumptions": "p=0.5 (max variance), random sampling"}. Use before collecting data, to size a survey. Not for analyzing data already collected (stats_describe, confidence_interval). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""} (for example {"error": "confidence_pct must be 90, 95, or 99"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry. ``` ## Only reads (5) Looks things up and changes nothing. Claude Code: allow. ### `get_free_skill` - The name "get_free_skill" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text Load a product's free gateway skill with its complete instructions. FREE. Typical input {"slug": "thesis-advisor"} returns {"slug": ..., "skill": "", "instructions": ""}. Returns exactly one skill - the product's free gateway skill - chosen automatically from the slug, with no plan required. Use when the caller wants usable instructions immediately. Not for the product's other skills: those are named and need get_full_skill with a skill_name, which requires a paid plan. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""} (for example {"error": "unknown slug ''. Use list_products."}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry. ``` ### `get_full_product` - The name "get_full_product" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text Load one product in full: its persona plus every paid skill. PREMIUM (license). Typical input {"slug": "thesis-advisor"} returns {"slug": ..., "name": ..., "persona": "", "skills": [{"name": ..., "instructions": ...}, ...], "free_skill": {...}}. Returns persona plus every skill for one product. Use when the caller wants the whole product. Not for a single skill (get_full_skill) and not for a free look, which list_products and get_free_skill provide with no plan. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""} (for example {"error": "unknown slug ''"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry. ``` ### `get_full_skill` - The name "get_full_skill" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text Load one paid skill's complete instructions from a product. PREMIUM (license). Typical input {"slug": "thesis-advisor", "skill_name": "Outline Builder"} returns {"slug": ..., "skill": ..., "instructions": ""}. Returns one named skill, selected by skill_name. Use when the caller wants one specific paid skill. Not for the free gateway skill, which get_free_skill returns with no plan, and not for every skill at once (get_full_product). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""} (for example {"error": "unknown slug ''"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry. ``` ### `list_products` - The name "list_products" says "list": a word for reading. Description, as the server wrote it: ```untrusted-server-text List every product in the Research Desk line with its included skills. FREE. Takes no arguments. Returns a list of 7 product objects, each {"slug": "thesis-advisor", "name": ..., "tagline": ..., "skills": ["Skill A", ...], "free_skill": "Gateway Skill Name"}. Use the returned slug values with get_free_skill, get_full_product, or get_full_skill. Returns metadata only - no persona text and no skill instructions. Use when the caller wants to see what this server covers. Not for keyword search across the whole 138-product catalog, which the catalog server's search_catalog does, and not for instructions the caller can act on (get_free_skill). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry. ``` ### `stats_describe` - The name "stats_describe" says "describe": a word for reading. Description, as the server wrote it: ```untrusted-server-text Describe a numeric dataset: center, spread, quartiles, and outliers. FREE. Typical input {"numbers": [12, 15, 14, 90, 13]} returns {"n": 5, "mean": 28.8, "median": 14.0, "std_dev": ..., "min": 12, "max": 90, "q1": ..., "q3": ..., "iqr_outliers": [90], "skew": "right (mean > median)"}. Use as a first summary of one numeric dataset. Not for interval estimates (confidence_interval) and not for planning a study (sample_size). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""} (for example {"error": "no numbers"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry. ``` ## Claude Code permissions For `.claude/settings.json`, assuming the server is installed as `research`: ```json { "permissions": { "allow": [ "mcp__research__list_products", "mcp__research__get_free_skill", "mcp__research__get_full_product", "mcp__research__get_full_skill", "mcp__research__stats_describe" ], "ask": [ "mcp__research__format_citation", "mcp__research__sample_size", "mcp__research__confidence_interval" ], "deny": [] } } ```