servers / ai-mcp-server
ai-mcp-server
communityunknownpythonwrite capablehealthy
本地 MCP 橋樑：把多個 API key + endpoint 收編為統一的模型能力池，給 Agent 透過 MCP 調用
01Tools · 6
How to read this: tool names here are observed from a live tools/list handshake. The Risk label is a heuristic inferred from the tool name (write/destructive verbs), not from executing the tool — a conservative guess, not a verified capability. We never escalate risk from a description. Found one that's wrong? Tell us — we fix on report.
| Tool | Risk | Side effects | Approval |
|---|---|---|---|
| invoke_model Forward a request to the selected (endpoint, model).
Args:
endpoint: endpoint name registered via the CLI.
model: model_id as returned by list_models.
operation: one of chat / embedding / image_gen / tts / stt / rerank.
payload: upstream-compatible body (OpenAI shape for openai-compat
endpoints). The `model` field is set automatically. The response
is passed through verbatim; errors are returned inside `error`.
| write | true | unknown |
| refresh_endpoint Enqueue probe jobs. Server-internal worker will drain them.
Args:
endpoint: endpoint name; if None, refresh every endpoint.
capabilities: list of capability tags; if None, choose probes per model using known metadata.
refresh_model_list: re-fetch /v1/models first (default True).
| read | false | unknown |
| usage_guide Return current capability inventory and usage instructions.
Call this first whenever you connect.
| unknown | unknown | unknown |
| model_performance Return近3天 aggregated call metrics per model (background-updated).
Args:
endpoint: limit to a single endpoint name.
sort_by: one of call_count / success_count / avg_first_byte_ms /
avg_prompt_tokens / avg_output_tokens.
limit: max rows to return.
Each row includes call_count, success_count, success_rate,
avg_first_byte_ms, avg_prompt_tokens, avg_output_tokens, window_days.
| unknown | unknown | unknown |
| list_models List models matching the filters.
Args:
capability: capability tags the model must support (e.g. ["vision"]).
min_context_length: minimum context window in tokens.
endpoint: limit to a single endpoint name.
include_unprobed: include models whose capabilities have not been
probed yet (default True).
| read | false | unknown |
| add_models Manually register models or user-confirmed model features.
Args:
endpoint: endpoint name.
model_ids: one or more model_id to register.
context_length: optional context window in tokens.
capabilities: optional capability tags to mark as supported
(override source). Aliases tts/stt/asr are accepted.
feature_overrides: optional key/value overrides. Keys may be
capability tags or context_length; capability values must be
booleans. Example: {"audio_tts": true, "context_length": 32000}.
| write | true | unknown |
02Install & source
uvx ai-mcp-server
uvxpip install ai-mcp-server
pip- repohttps://github.com/brianMacao/ai-mcp-server
- packagehttps://pypi.org/project/ai-mcp-server
- homepagehttps://github.com/brianMacao/ai-mcp-server
- licenseMIT
- adoption0 stars · 0 forks
03Access granted
Generate images · writeVector & semantic search · write
The access this server can exercise, inferred from its verified tools — not a declared OAuth scope.
05Provenance & freshness
sourcesPyPI [p4]
last_checked2026-08-16 19:31Z
next_check2026-08-16 22:31Z
cadenceevery 3h
verifiedhandshake:failed metadata:passed handshake:failed metadata:passed handshake:failed metadata:passed handshake:failed metadata:passed handshake:failed metadata:passed
index_statusindex — 9 unique facts >= 5
06Badge
Add the “as seen on MCPExplorer” badge to your README. 
[](https://mcpexplorer.com/servers/ai-mcp-server)
Next step
This is one server. A loadout combines the right servers, governance, and proven plays for a whole job — assembled deliberately, not tool-dumped.
Explore loadouts →