{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_27afu3gq6zmy","handle":"glm-mcp","url":"https://wellknown.network/agents/glm-mcp","links":{"self":"https://wellknown.network/agents/glm-mcp/record.json","html":"https://wellknown.network/agents/glm-mcp","markdown":"https://wellknown.network/agents/glm-mcp/record.md","api":"https://wellknown.network/api/v1/agents/glm-mcp","status":"https://wellknown.network/api/v1/agents/glm-mcp/status","claim":"https://wellknown.network/agents/glm-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/glm-mcp/claim.json","badge":"https://wellknown.network/agents/glm-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/glm-mcp/history","tools":"https://wellknown.network/api/v1/agents/glm-mcp/tools"},"ard":{"identifier":"urn:air::server:glm-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"glm-mcp","summary":"MCP server for ZhipuAI GLM — chat, text embeddings, translation, vision, and OCR","description":"# glm-mcp\n\nMCP server for [ZhipuAI GLM](https://open.bigmodel.cn/) — exposes chat, text embeddings, translation, vision, and OCR to Claude Code (and any MCP-compatible client) via the OpenAI-compatible API.\n\n## Tools\n\n| Tool | Description |\n|------|-------------|\n| `glm_chat` | Text completion — default model `glm-4-flash`, pass `model=` to use any GLM chat model (e.g. `glm-5`). Supports single-turn and multi-turn (`messages=` parameter). Sampling: `temperature=0.7`, `top_p=0.95` (pass `top_p=None` to omit). Auto-fallback on transient errors (429/503/timeout/connection) via `auto_fallback=True` (default). Use `avoid_peak_hours=True` to pre-emptively switch during peak hours (UTC+8 14:00–18:00). |\n| `glm_embed` | Text embeddings — default model `embedding-3`, pass `model=` to override |\n| `glm_usage_summary` | Query token usage from `~/.glm-mcp/usage.jsonl`. Parameters: `days` (default 7), `model` (optional filter). Returns period, total tokens, by_tool, by_model. |\n| `glm_translate` | Pure single-language translation — default model `glm-4.7`. Parameters: `text`, `target_lang` (`\"ja\"`, `\"zh\"`, `\"en\"`), `source_lang` (default `\"auto\"`), `style` (`\"formal\"` or `\"casual\"`, default `\"formal\"`). Sampling: `temperature=1.0`, `top_p=0.8` (GLM-4.7 Plan B: top_p as primary control; pass `top_p=None` to omit). Outputs ONLY the target language, solving the mixed Chinese–Japanese output problem common with general LLMs. |\n| `glm_vision` | Multimodal image analysis — default model `glm-4.6v`. Parameters: `image_url` (HTTP/HTTPS URL or Base64 string), `prompt`, `detail` (`\"auto\"`, `\"low\"`, `\"high\"`), `max_tokens` (default 2048). Sampling: `temperature=0.2`, `top_p=0.9` (focused stable analysis; pass `top_p=None` to omit). Auto-fallback to `glm-4.6v-flash` on 429/503/timeout. Bare Base64 strings are automatically prefixed with `data:image/png;base64,`. |\n| `glm_ocr` | Document and image OCR — default model `glm-ocr`. Parameters: `file` (HTTP/HTTPS URL, Base64 string, `data:` URI,…","publisher":null,"homepage":null,"repository":null,"version":"0.8.1","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:glm-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"content.translation","name":"Translation","confidence":0.871,"provenance":"derived"},{"slug":"media.image-understanding","name":"Image Understanding","confidence":0.848,"provenance":"derived"}],"categories":["content","media"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"glm-mcp","registry":"pypi","observedAt":"2026-10-21T23:25:11.041Z","publishedAt":"2026-03-01T11:38:49.303893Z","latestVersion":"0.8.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"glm-mcp","url":"https://pypi.org/project/glm-mcp/","firstSeenAt":"2026-09-09T16:24:05.579Z","fetchedAt":"2026-10-21T23:23:51.438Z","normalizedAt":"2026-10-21T23:23:51.438Z"}]},"firstSeenAt":"2026-09-09T16:24:05.579Z","updatedAt":"2026-10-21T23:25:11.041Z"}