add-an-mcp-tool

add-an-mcp-tool is a skill for Claude Code, Codex from ArkaAiAdmin/Agentic-Memory. It costs 84 tokens per session (2,126 once invoked), scanned A, original, Apache-2.0.

A maintainer procedure for adding a new MCP tool, which is a callable operation exposed to an AI agent.

In plain words
What is it for?
It is for adding read, maintenance, or administrative operations to the agentic-memory MCP server and checking them with tests and drift validation.
Why use it?
It gives developers the required places to implement, register, test, and verify a new tool so the tool inventory stays consistent.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions OpenCode.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/arkaaiadmin/agentic-memory/add-an-mcp-tool
Any agent
npx skills add ArkaAiAdmin/Agentic-Memory --skill add-an-mcp-tool
Clone the repo
git clone --depth 1 https://github.com/ArkaAiAdmin/Agentic-Memory

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for add-an-mcp-tool

README.md
[![agentmods](https://agentmods.dev/badge/skills/arkaaiadmin/agentic-memory/add-an-mcp-tool.svg)](https://agentmods.dev/skills/arkaaiadmin/agentic-memory/add-an-mcp-tool)
Your own site
<a href="https://agentmods.dev/skills/arkaaiadmin/agentic-memory/add-an-mcp-tool"><img src="https://agentmods.dev/badge/skills/arkaaiadmin/agentic-memory/add-an-mcp-tool.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,126 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00084 $0.02126
Opus 5 $0.00042 $0.01063
Sonnet 5 $0.00017 $0.00425
Haiku 4.5 $0.00008 $0.00213

Measured 5d ago against content hash b050b33cd21f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

add-an-mcp-tool scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/add-an-mcp-tool/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add an MCP Tool

How to add a new tool to the agentic-memory MCP server. There are 70 tools today; this is the canonical way to add a 71st.

The 60-second version

  1. Implement the function in the appropriate mcp_*.py module (search, kg, safety, retention, profile, etc.) or in mcp_maintenance.py for admin ops.
  2. Decorate with @mcp.tool().
  3. If it's a CORE tool, add it to tool_registry.CORE_TOOLS. If it's an ADMIN op, route it through memory_maintenance(operation=...) by adding a handler in mcp_maintenance_ops.py.
  4. Re-export the new function from mcp_tools.py (the canonical tool inventory).
  5. Add a test in eval/test_*.py (match the existing patterns).
  6. Run scripts/tool_drift_check.py to verify registration consistency.
  7. Run pytest eval/ -q to verify no regressions.

Total: ~30 minutes for a simple read tool, ~2 hours for a complex write tool.

Step 1: decide CORE vs ADMIN

CORE tools (always exposed, 15 user-facing verbs):

  • Read: memory_search, memory_semantic_search, memory_recall_context, memory_facts_search, memory_graph_search, memory_session_start, memory_user_profile
  • Write: memory_save, memory_supersede, memory_delete, memory_restore
  • Safety/admin: memory_check_contradictions, memory_scan_injection, memory_rebuild, memory_profile_access

ADMIN tools (55 total, grouped under memory_maintenance(operation=...); 9 added 2026-06-22):

  • All maintenance ops: heartbeat, compact, consolidate, backfill_all, rebuild, check_integrity, purge_expired, duplicates, merge_suggestions, rewrite_links, tier_stats, review_schedule, pinned_decay, retention_stats, profile_stats, auto_summarize, summarize, daily_digest, compile_skill, share, shared_list, shared_stats, strip_provenance, trash, restore, etc.

Rule of thumb:

  • Does the user-agent invoke this in normal conversation? → CORE
  • Does only the maintainer / dev-tools / cron invoke this? → ADMIN
  • Is it a verb-noun the user can name (memory_save, memory_search)? → CORE
  • Is it a noun-modifying operation (backfill_all, consolidate, purge)? → ADMIN

Read the full file on GitHub · 189 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 189 lines · 84 tokens per session scan A b050b33cd21f

Subscribe to this mod's changes

add-an-mcp-tool is a skill published in the GitHub repository ArkaAiAdmin/Agentic-Memory (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 84 tokens to every session and 2,126 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens