{"version":"2.1.248","anchor":"mcp-output-token-cap-resolution","canonical_anchor":"mcp-output-token-cap-resolution","heading":"MCP output token cap resolution","tier":"use","area":"MCP","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.248\/e\/mcp-output-token-cap-resolution","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.248","markdown":"### MCP output token cap resolution\n\nMAX_MCP_OUTPUT_TOKENS is still honoured first, but it's no longer sanity-checked as a number.\n\n**What**\n\nThe limit on how much output an MCP tool may return still reads the `MAX_MCP_OUTPUT_TOKENS` environment variable first, then a server-side config value, then a built-in default. The environment value is no longer checked for being a finite number before use.\n\n**Details**\n\n- Server config comes from `tengu_velvet_ibis`, whose fallback is an empty object, so with no server value the built-in default applies.\n\n**Evidence**\n\n`tengu_velvet_ibis`\n\n- Flag `tengu_velvet_ibis`: Not enough to say (read for one account on one subscription tier against v2.1.248; this account: no value returned, anonymous baseline: no value returned, compiled default: not a boolean we can read)\n- Area: MCP\n- Names: `MAX_MCP_OUTPUT_TOKENS`\n- Tier: Use it now\n- Useful: 2\/5\n- Signal: 1\/5"}