--- title: MCP Tool-List Token Calculator: Claude Code, Codex, OpenCode description: Paste your MCP tools/list to estimate what it adds per request in Claude Code, Codex and OpenCode, using per-app factors measured on a 99-tool list. In-browser. canonical: https://spiritroom.app/tools/mcp-token-cost/ published: 2026-10-21 updated: 2026-10-21 --- > Markdown version of https://spiritroom.app/tools/mcp-token-cost/ for agents. Index: /llms.txt [Blog](/blog/) / [How agents load MCP tools](/guides/how-agents-load-mcp-tools/) # MCP tool-list token calculator: what your tools cost in Claude Code, Codex and OpenCode Your tool list has one size. What it costs depends on the agent app: one app sends it with every request, another sends only names, another sends nothing until the model searches. Paste your list to see the spread. Leonid Bugaev · Published 21 Oct 2026 **TL;DR** - **Paste tools/list,** get a rough token size and a per-app estimate per request and per question. Nothing leaves your browser. - **Factors are measured:** with a 99-tool list of 68,730 tokens, OpenCode 1 added 73,415 per request, Claude Code with tool search off 107,541, with it on 1,715, Codex 0. - **Every request:** preloading apps resend the list each time; OpenCode averaged 3.7 requests per question in our runs. - **Estimates, not counts:** tokens are characters ÷ 4; app factors come from one list each. Re-measure for real decisions. [Calculator](#calc)[Where the factors come from](#factors)[How to read the result](#read)[How we measured](#how-we-measured)[FAQ](#faq) ## Calculator Paste a `tools/list` response or its `tools` array. Everything runs in this page. Model requests per question: Estimate Need the JSON? Use [MCP Inspector](https://modelcontextprotocol.io/docs/draft/tools/inspector) or its CLI to print the `tools/list` result. Checks beyond size: [MCP server scorecard](/tools/mcp-scorecard/). **Want measured numbers, not estimates?** We capture what each agent app actually sends with your server attached, job by job, and show what to trim. [Measure your MCP →](/#contact) ## Where the factors come from We served a recorded 99-tool list from a local mock server, sent “say hi” with and without it, and compared each app's first-request input tokens. | App and mode | Without | With 99 tools | Added | | --- | --- | --- | --- | | Codex 0.161.0, default code mode | 17,098 | 17,098 | 0 | | Claude Code 2.1.301, default | 21,076 | 22,791 | +1,715 | | Claude Code, `ENABLE_TOOL_SEARCH=false` | 36,474 | 144,015 | +107,541 | | Claude Code, custom `ANTHROPIC_BASE_URL` | 35,911 | 143,453 | +107,542 | | OpenCode 1.18.34, default | 12,265 | 85,680 | +73,415 | The list itself was 68,730 tokens (o200k\_base). Each app counts with its own tokenizer, which is why the added figures differ from the list size. ## How to read the result - **Preloading apps pay it every request.** Multiply by requests per question. In our live runs OpenCode averaged 3.7; Codex took 4.2–7.6 depending on the job. - **Search-based apps pay later,** in search output and loaded definitions, and their cost depends on names and first lines more than size. See [Claude Code tool search, seen from the wire](/blog/claude-code-tool-search-explained/). - **A few heavy tools often dominate.** In our example, two tools were 35% of the list. See [how many MCP tools is too many](/blog/how-many-mcp-tools-is-too-many/). **Go deeper:** [MCP context window usage](/blog/mcp-context-window-usage/), [OpenCode 1 vs 2](/blog/opencode-mcp-tool-loading/), [Per-task cost, Claude Code vs Codex](/blog/mcp-task-token-cost-claude-code-vs-codex/). Back to [how agents load MCP tools](/guides/how-agents-load-mcp-tools/). ## How we measured - **Controls:** 16 Oct 2026, mock server serving a recorded 99-tool list, prompt “say hi”, first-request input tokens by each app's own usage. - **Calculator:** your list's estimated tokens × (added ÷ 68,730) for preloading apps; 1,715 ÷ 99 per tool for names-only. Codex shown as 0 up front. - **Limits:** one list, one version per app, single runs. Treat results as a rough guide. ## FAQ ### How many tokens does my MCP server's tool list use? Paste the tools/list JSON into the calculator: it estimates tokens as compact JSON characters ÷ 4. For an exact count, use the tokenizer of the model you care about. ### Do all agent apps pay for the whole tool list? No. In our measurements OpenCode 1 and Claude Code with tool search off sent every definition with every request; Claude Code with tool search on sent only names (about 17 tokens per tool); Codex sent nothing up front and found tools by search. ### When does Claude Code turn tool search off? In our tests, with ENABLE\_TOOL\_SEARCH=false and when it ran through a custom ANTHROPIC\_BASE\_URL (a proxy or gateway). Then all 99 definitions were in every request. ### Is the calculator exact? No. It scales factors measured on one 99-tool list by your list's size. Tokenizers differ by model, and apps change between versions. **Want measured numbers, not estimates?** We capture what each agent app actually sends with your server attached, job by job, and show what to trim. [Measure your MCP →](/#contact) ## Keep reading - Up[How agent apps load MCP tools: what the model sees (guide)](/guides/how-agents-load-mcp-tools/) - Related[How many MCP tools is too many? Real token costs across five agents (2026)](/blog/how-many-mcp-tools-is-too-many/) - Related[Free MCP server scorecard: paste your tools/list, get size, annotation and description checks](/tools/mcp-scorecard/)