MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Config-first setup wizard for a remindb MCP server — run it as /remindb-setup (interactive), /remindb-setup automode (hands-off), or /remindb-setup only-config (bridge hosts: author .remindb/ only…
$ npx skills add radimsem/remindb --skill remindb-setup -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install radimsem/remindb remindb-setup --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/radimsem/remindb.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/remindb-setup .claude/skills/remindb-setup && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "remindb-setup" agent skill from https://github.com/radimsem/remindb/tree/dev/skills/remindb-setup into .claude/skills/remindb-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "remindb-setup", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/radimsem/remindb/tree/dev/skills/remindb-setupType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add radimsem/remindb --skill remindb-setup -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install radimsem/remindb remindb-setup --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/radimsem/remindb.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/remindb-setup .agents/skills/remindb-setup && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "remindb-setup" agent skill from https://github.com/radimsem/remindb/tree/dev/skills/remindb-setup into .agents/skills/remindb-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "remindb-setup", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add radimsem/remindb --skill remindb-setup -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install radimsem/remindb remindb-setup --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/radimsem/remindb.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/remindb-setup .cursor/skills/remindb-setup && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "remindb-setup" agent skill from https://github.com/radimsem/remindb/tree/dev/skills/remindb-setup into .cursor/skills/remindb-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "remindb-setup", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/radimsem/remindb.git --path skills/remindb-setup--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add radimsem/remindb --skill remindb-setup -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install radimsem/remindb remindb-setup --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/radimsem/remindb.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/remindb-setup .gemini/skills/remindb-setup && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "remindb-setup" agent skill from https://github.com/radimsem/remindb/tree/dev/skills/remindb-setup into .gemini/skills/remindb-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "remindb-setup", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install radimsem/remindb remindb-setupInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add radimsem/remindb --skill remindb-setup -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/radimsem/remindb.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/remindb-setup .github/skills/remindb-setup && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "remindb-setup" agent skill from https://github.com/radimsem/remindb/tree/dev/skills/remindb-setup into .github/skills/remindb-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "remindb-setup", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add radimsem/remindb --skill remindb-setup -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install radimsem/remindb remindb-setup --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/radimsem/remindb.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/remindb-setup .opencode/skills/remindb-setup && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "remindb-setup" agent skill from https://github.com/radimsem/remindb/tree/dev/skills/remindb-setup into .opencode/skills/remindb-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "remindb-setup", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
remindb-setupConfig-first setup wizard for a remindb MCP server — run it as /remindb-setup (interactive), /remindb-setup automode (hands-off), or /remindb-setup only-config (bridge hosts: author .remindb/ only…
Remindb Setup is an agent skill from radimsem/remindb. Config-first setup wizard for a remindb MCP server — run it as /remindb-setup (interactive), /remindb-setup automode (hands-off), or /remindb-setup only-config (bridge hosts: author .remindb/ only, no env wiring). Two passes. First-time (no server attached yet): detect the host, author the .remindb/ config (ignore/pinned/temperatures/config.json) BEFORE compiling, compile the source, seed adjacent context, install the MCP plugin, then wire the MCP env. Verify (server attached): MemoryStats + remindb://doctor…
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/automode-playbook.md`, `references/config-examples.md` and `references/config-model.md`).
It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The repository describes itself as: An agentic memory database that cuts session tokens by 82–99%. One portable SQLite file — your agent's memory, anywhere. The licence is MIT.
8 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 977b31c. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
npxcodexFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Remindb Setup loads about 2.2k tokens when it runs, and up to ~8.3k if it reads all its reference files. Until then it costs about 205 tokens; SKILL.md has 1,041 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from radimsem/remindb at commit 977b31c, republished under its MIT licence (© radimsem). 1,041 words, ~2,235 tokens.
.claude/skills/remindb-setup/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.You are the wizard. This skill is the script you follow to set up or reconfigure a remindb workspace from inside a live session — there is no separate UI. Drive it with Bash + the Memory* tools + file writes.
--help firstBefore invoking any remindb subcommand, confirm its flags with remindb <subcommand> --help (remindb compile --help, remindb inspect --help, …). Don't trust remembered syntax — silently-wrong positional args are the wizard's most common footgun (e.g. remindb inspect <path> is ignored; the flag is --db <path>, and the default memory.db quietly opens an empty file in CWD).
remindb ships as two independently-installed halves: the skill (this, via npx skills add) and the MCP plugin (per host). The skill installs first and can run before the plugin is attached — that's what makes config-first ordering possible. Detect the pass by whether the server is attached this session:
Memory* tools absent from your available tool set → Pass 1: first-time config-first setup (§Pass 1). The default first run.Memory* tools present → Pass 2: verify / reconfigure (§Pass 2)./remindb-setup — interactive: propose each choice for approval before writing./remindb-setup automode — infer every parameter, write directly, then report. The trust actions it still confirms: running the remote installer (step 1), invoking plugin install (step 7), and writing host MCP config (step 8). Inference rules → references/automode-playbook.md./remindb-setup only-config — bridge-host short-circuit: run Pass 1 steps 1–4 only (binary → host → source → .remindb/), then stop with a one-line summary. Parses Source root: (mandatory; absent → fail loud, interactive or automode — don't guess) and Also adjacent-seed: (optional, newline-separated absolute paths queued for the calling host to compile later) from the prompt body. Composable with automode. Use when the calling host owns compile + plugin install + env wiring via its own pipeline — see the bridge-host note in references/host-wiring.md; parsing rules in references/automode-playbook.md.Not every host surfaces this as a literal /remindb-setup command — invoke it per the host's row in references/host-wiring.md. The wizard runs the same once invoked.
Order matters: author .remindb/ before compiling, so ignore/pinned/temperatures.json apply at insert time — no --reseed retrofit. only-config truncates this list to steps 1–4 and stops with a summary (see Mode above).
remindb --version (Bash). Missing → install it; confirm before the remote installer, even in automode. One-liners + PATH detail → references/config-model.md §Bootstrap./plugin install = Claude Code; /skills picker = Codex; openclaw mcp = OpenClaw; activate_skill = Gemini CLI; OpenCode activates skills via plain language). For host-specific config paths, lean on your runtime's own knowledge first — system prompt, loaded host-specific skills, runtime docs — rather than probing the filesystem. If runtime context is still ambiguous, ask the user (automode: pick the most likely and record the assumption). Then look up the matching row in references/host-wiring.md..remindb/ lives. You're pre-attach, so there's no REMINDB_SOURCE to read yet; settle it with the user (automode: infer from the host's state dir, e.g. ~/.claude/projects)..remindb/. Write ignore / pinned / temperatures.json / config.json at <source>/.remindb/. Semantics + how each change lands → references/config-model.md; copy-pasteable templates per workspace type → references/config-examples.md. Interactive: show the plan first. automode: write, then summarize each non-obvious choice.remindb compile <source> --db <db> — insert-time apply; no --reseed (the config is already in place).CLAUDE.md / AGENTS.md / GEMINI.md / README.md — won't be in the DB. Offer to fold them in via the CLI (you're pre-attach, so MemoryCompile the tool isn't available yet), one per file, absolute paths:remindb compile /abs/path/CLAUDE.md --db <db>Plugin install column in references/host-wiring.md (e.g. /plugin install remindb@remindb for Claude Code, codex plugin marketplace add radimsem/remindb for Codex). Where the install command is Bash-callable the wizard can run it; for Claude Code the wizard prompts the user (/plugin install isn't a shell command). Confirm before invoking install. Plugin must be installed before step 8 wherever the loaded config is post-install (Claude Code cache, OpenClaw MCP store).REMINDB_DB / REMINDB_SOURCE in the loaded config file. Locate the file first — references/host-wiring.md names it per host; for unknown hosts probe grep -rl REMINDB <host-config-dir>. Don't trust memory. Scoped edit preferred (multi-brain safe); shell-export fallback only when scoped isn't viable (unknown host, or user opt-in for Claude Code marketplace) — see §Env-wiring principle in host-wiring.md. Confirm before writing host config, even in automode. Then reload the host.Close Pass 1 by telling the user that once the host has reloaded, the server attaches with REMINDB_DB/REMINDB_SOURCE resolved — re-run the wizard (Pass 2) to confirm MemoryStats db_path matches the compiled DB.
MemoryStats() → confirm the reported database path is the one you compiled and node count is non-zero; then read remindb://doctor for FTS5 / stale-root checks (for a machine-checkable path, remindb://overview exposes a db_path field). Cold-node notifications need a one-shot SetLoggingLevel (logging/setLevel) from the client — most send it automatically; if yours doesn't, the server is fine but the client must opt in (detail → references/config-model.md).db_path mismatch / 0 nodes. MemoryStats reports a db_path that's not the compiled DB — especially a literal $PWD/${REMINDB_DB} with 0 nodes (the Claude Code shape: cache ${VAR} passthroughs evaluated against a shell where the var is unset) — means the env didn't resolve where the server launched: either the env var is unset, or you edited the wrong config file. Fix: set REMINDB_DB/REMINDB_SOURCE in the actually-loaded config (re-check references/host-wiring.md for which file that is on your host) or in the launch shell, then reload..remindb/ file, then apply per the 3-tier model in references/config-model.md: live-reload (temperature/rescan) → nothing; insert-time (temperatures.json/pinned) → reseed (below); frozen (budgets/server/redaction) → restart.temperatures.json/pinned after the fact does nothing to already-compiled nodes. To apply them to an existing DB:remindb compile <source> --db <db> --reseed-temperatures --reseed-pinned--reseed-pinned re-applies .remindb/pinned to every match, overwriting manual MemoryUnpin choices. WAL + busy_timeout(5s) makes it safe while serve holds the file. MemoryCompile (the tool) never reseeds pins — hence the CLI.Done? You're ready: remember (plain-language front door), remind (read tools), memorize (write tools).
© radimsem, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 4 other files (references) in skills/remindb-setup of radimsem/remindb.
Open the folder on GitHubat commit 977b31c
Remindb Setup next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Remindb Setup this skillradimsem/remindb | 129 | — | ~2.2k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 62 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 5 repos | ~1.2k | Automated safety check: Pass | MIT | |
| MCP Integration for Pluginsanthropics/claude-plugins-official | 37k | 11 repos | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| Fastmcp Client CLIPrefectHQ/fastmcp | 28k | 1 repos | ~823 | Automated safety check: Pass | Apache-2.0 | |
| Crush Configurationcharmbracelet/crush | 29k | — | ~3.7k | Automated safety check: Pass | Custom licence |
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
anthropics/claude-plugins-official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
PrefectHQ/fastmcp
Query and invoke tools on MCP servers using fastmcp list and fastmcp call.
charmbracelet/crush
Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
radimsem/remindb
Guides an agent writing to a remindb memory server: structured notes go in as files parsed into a node tree, single text facts go in through MemoryWrite.
radimsem/remindb
Covers the read-side tools of the remindb MCP server, a SQLite-backed agent memory, for orienting, searching, resyncing and tracing relations.
radimsem/remindb
Adds a new row to remindb's token-savings benchmark table by writing a scenario function that measures the naive shell-tool token cost against the remindb tool-call cost for the same task.
radimsem/remindb
Adds a new Go fuzz target to remindb following its seed-corpus discipline: one target per logical surface, discovered automatically by its FuzzXxx function name.
radimsem/remindb
Explains how to add an end-to-end test scenario to remindb, choosing between a direct API test and an MCP test and using the shared helpers and fixtures.
radimsem/remindb
Checklist for adding a new Memory-prefixed tool to remindb's Go MCP server: tool file, registration, test, skill docs, plus the locking and logging rules.
Works with
Categories
Config-first setup wizard for a remindb MCP server — run it as /remindb-setup (interactive), /remindb-setup automode (hands-off), or /remindb-setup only-config (bridge hosts: author .remindb/ only…. Remindb Setup is an agent skill from radimsem/remindb.remindb/ only, no env wiring).
Remindb Setup fits situations like: tasks that involve MCP servers.
Run `npx skills add radimsem/remindb --skill remindb-setup -a claude-code`. Or copy the skill folder (skills/remindb-setup in radimsem/remindb) into .claude/skills/remindb-setup in your project. Claude Code loads it when a task matches its description.
Run `npx skills add radimsem/remindb --skill remindb-setup -a codex`. Or copy the skill folder (skills/remindb-setup in radimsem/remindb) into .agents/skills/remindb-setup in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add radimsem/remindb --skill remindb-setup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/remindb-setup, .gemini/skills/remindb-setup, .github/skills/remindb-setup and .opencode/skills/remindb-setup in your project.
Going by SKILL.md and its folder, Remindb Setup needs the command-line tools its instructions call (npx and codex). Our summary lists: Node.js.
SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Remindb Setup is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.1k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Remindb Setup: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 37k stars) and Fastmcp Client CLI (PrefectHQ/fastmcp, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
radimsem (a GitHub user) maintains it in radimsem/remindb, which has 129 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on August 3, 2026.
Source: radimsem/remindb on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.