Repository navigation
Description
What happened?
call_tool_read / call_tool_write / call_tool_destructive declare args as
{"type": "object", "properties": {}} (from mcp.WithObject("args", ...) in internal/server/mcp.go, still
the case on main as of 2026-09-24). Clients that turn tool schemas into a constrained-decoding grammar read an empty
properties map as "an object with no keys allowed", so the model can only ever emit "args": {}. Every call then
fails with missing property 'path' (or similar), and the retry loops forever.
Cloud models (no grammar) are unaffected, which is probably why this has not come up.
Not a duplicate of #982 / PR #988. That fix made upstream tools' own schemas show up correctly in the REST/CLI
listings (supervisor ParamsJSON stub), and it works: retrieve_tools returns full upstream schemas. This issue is the
args parameter of the call_tool_* meta-tools themselves, declared in internal/server/mcp.go, which #988 did not touch.
Expected behavior
The args parameter of call_tool_read / call_tool_write / call_tool_destructive should be declared as an open
object (e.g. {"type":"object","additionalProperties":true}, or with no "properties" key), so clients that compile
tool schemas into a constrained-decoding grammar (llama.cpp llama-server) let the model emit the upstream tool's
arguments, e.g. "args": {"path": "...", "head": 3}.
Actual: the schema is {"type":"object","properties":{}}, which llama.cpp's grammar treats as "no keys allowed",
so the model can only emit "args": {} and every call fails with "missing property 'path'".
Steps to reproduce
1.- mcpproxy v0.66.1 (Windows), /mcp endpoint (retrieve_tools + call_tool_*)
2.- llama.cpp llama-server (OpenAI-compatible /v1/chat/completions with tools), Qwen3.5 9B and Qwen3.6 35B-A3B
Minimal test with the tool schema alone, same prompt, temperature 0, two tries each:
args schema sent to llama.cpp |
what the model emitted |
|---|---|
{"type":"object","properties":{}} (as mcpproxy sends it) |
"args":{} — both times |
{"type":"object"} |
"args":{"path":"D:/x.md","head":3} — both times |
{"type":"object","properties":{},"additionalProperties":true} |
"args":{"path":"D:/x.md","head":3} — both times |
End to end through mcpproxy (5 read-only tasks): with the schema as served, the 35B scored 2 of 5 correct and only
escaped by falling back to args_json after 4–12 empty calls; a 9B model scored 0 of 3. With only that one schema
change made on the client side, the same 35B completed 30 of 30 runs correctly across six sampling settings.
===
Suggested fix
Declare args as an open object, e.g.
mcp.WithObject("args",
mcp.Description("..."),
mcp.AdditionalProperties(true),
),
or omit properties for this parameter. Either form lets constrained decoders emit arbitrary keys, and it should not
change behaviour for any other client.
Workaround for others hitting this
Use args_json (string), or strip the empty properties from the schema before handing tools to the model.
MCPProxy version
0.66.1
Operating system
macOS
Relevant logs
mcpproxy doctor?
Yes, on v0.66.1 (windows/amd64, personal edition), 2026-09-25, against the running service:
Version: v0.66.1
✅ All systems operational! No issues detected.
Routing Mode (configured): retrieve_tools
Endpoints: /mcp/all (direct), /mcp/code (code_execution), /mcp/call (retrieve_tools)
✓ Sensitive Data Detection: enabled (default)
Doctor reports healthy, as expected: all upstreams connect and calls made with args_json succeed. The fault is in
the meta-tool schema the MCP endpoint serves, which doctor doesn't check.
Pre-submission checklist
- I searched existing issues and did not find a duplicate
- I ran
mcpproxy doctorand reviewed the output
Activity
Dumbris commentedon Sep 30, 2026
Thank you @2eestunes-tech for this excellent report! The minimal A/B table and the root-cause pointer made this very quick to fix.
Fixed in #1434 (merged). What changed:
argsoncall_tool_read/call_tool_write/call_tool_destructiveis now declared as{"type":"object","additionalProperties":true}(no emptypropertiesmap).inputandoptionsoncode_execution, which had the same problem.We reproduced your result locally with llama.cpp
llama-server(Qwen3-8B,--jinja, temperature 0, forced tool call) using the realcall_tool_readschema:"args": {}(3/3)"args": {"path": "D:/notes/x.md", "head": 3}(3/3)It will ship in the next release. Until then,
args_jsonremains a working workaround. If you still see emptyargswith your setup after upgrading, please reopen this issue.fix(mcp): declare call_tool_* args and code_execution input/options a…
fix(direct): keep upstream additionalProperties/$defs on /mcp/all too…