MCP servers, over streamable HTTP

A server is a row with a URL; its tools are discovered by a button and
cached, then offered beside the built-in ones. Written by hand rather than
taken from the reference SDK, because that SDK's transport does its own
connecting -- and the one thing that must not be bypassed is check_url on
every hop. Owning the transport is the point; the framing beside it is the
small part.

Sessions are per call: initialize, initialized, the call, a best-effort
DELETE. Caching one wants an owner, a TTL, eviction, a lock and a shutdown
hook, and the server may expire it under all of that anyway -- ToolContext
is a session-free snapshot precisely so nothing in a tool holds live state.

A server's names and descriptions reach the model as instructions and are
bounded before they do; what it returns is escaped preformatted text, never
markdown. Tools are namespaced per server, so two servers exposing "search"
do not collide and neither shadows a built-in.

Also: a round's calls now run together under a semaphore, results indexed
so each tool turn stays paired with its call, and generation.status names
what is running -- a remote tool is latency-bound, and a silent pause is
what a hang looks like.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Jaroslav Beneš
2026-08-01 16:44:29 +02:00
parent d4cefb066a
commit ecadb66414
15 changed files with 2166 additions and 12 deletions
+185
View File
@@ -0,0 +1,185 @@
"""Turning MCP servers into tools a chat can be offered.
Two names per tool. The server has its own, which is what `tools/call` must be
given; we have an *offered* name, which is what goes in the schema the endpoint
sees. They differ because two servers both exposing `search` would collide, a
server exposing `notes_delete` would shadow a built-in, and endpoints accept a
narrower character set than MCP does. The rename never leaves this module: the
runner closes over the server's own name.
The advertised list is cached on the row and refreshed by a button, the same
shape as discovering a connection's models. A server is contacted when an
administrator asks, not when a chat starts -- a slow server must not be able to
delay every reply.
"""
from __future__ import annotations
import logging
import re
from datetime import UTC, datetime
from typing import Any
from sqlalchemy.orm import Session as DBSession
from lembas.db.models import McpServer, User
from lembas.services import tool_access
from lembas.services.fetch import FetchError
from lembas.services.mcp import client
from lembas.services.mcp.protocol import McpError
from lembas.services.tools import FAMILY_MCP, ToolContext, ToolDef, ToolOutcome
log = logging.getLogger(__name__)
# What an endpoint will accept as a function name.
FUNCTION_NAME = re.compile(r"^[a-zA-Z0-9_-]{1,64}$")
MAX_NAME = 64
# How much of a reply is kept on the message row for the transcript.
MAX_EVENT_CHARS = 2000
MAX_SUMMARY_CHARS = 200
def offer_name(server_slug: str, tool_name: str, *, taken: set[str]) -> str:
"""A name the endpoint will accept, unique across everything offered.
Truncation can collide where the full names would not, so a numeric suffix
is appended until it does not. Deterministic given a stable iteration order,
which is why rows are walked in (position, slug) order everywhere.
"""
combined = f"{server_slug}_{tool_name}".lower()
cleaned = re.sub(r"_+", "_", re.sub(r"[^a-z0-9_-]", "_", combined)).strip("_")
candidate = (cleaned or "tool")[:MAX_NAME]
suffix = 2
while candidate in taken:
tail = f"_{suffix}"
candidate = f"{(cleaned or 'tool')[: MAX_NAME - len(tail)]}{tail}"
suffix += 1
taken.add(candidate)
return candidate
def _summary(arguments: dict[str, Any]) -> str:
parts = [f"{name}={value!r}" for name, value in arguments.items()]
text = ", ".join(parts)
return text[:MAX_SUMMARY_CHARS]
def _runner(spec: client.McpSpec, tool_name: str, offered: str):
async def run(context: ToolContext, args: dict[str, Any]) -> ToolOutcome:
event = {
"name": offered,
"kind": "mcp",
"label": f"{spec.name} · {tool_name}",
"query": _summary(args),
"detail": spec.name,
"results": [],
}
try:
text, failed = await client.call_tool(spec, tool_name, args)
except (McpError, FetchError) as exc:
message = exc.message
log.info("mcp %s/%s failed: %s", spec.slug, tool_name, message)
return ToolOutcome(
f"The {tool_name} tool on {spec.name} failed: {message}",
{**event, "status": "error", "error": message[:200]},
)
text = text.strip()[: spec.max_chars]
if failed:
return ToolOutcome(
f"The tool reported an error:\n{text}" if text else "The tool reported an error.",
{**event, "status": "error", "error": text[:200] or "The tool reported an error."},
)
if not text:
return ToolOutcome(
f"{tool_name} returned nothing.", {**event, "status": "ok", "text": ""}
)
return ToolOutcome(text, {**event, "status": "ok", "text": text[:MAX_EVENT_CHARS]})
return run
def _offered_tools(server: McpServer) -> list[dict[str, Any]]:
"""The cached entries this server is currently willing to offer."""
overrides = server.tool_overrides_json or {}
# Absent means on, the rule the model capability flags follow: a tool that
# appeared in the last refresh should work rather than silently do nothing.
return [
entry
for entry in (server.tools_json or [])
if isinstance(entry, dict) and overrides.get(entry.get("name"), True)
]
def tool_defs(
db: DBSession, user: User | None, *, everything: bool = False, taken: set[str] | None = None
) -> list[ToolDef]:
"""One `ToolDef` per offerable tool across every visible server."""
claimed = taken if taken is not None else set()
out: list[ToolDef] = []
for server in tool_access.visible_mcp_servers(db, user, everything=everything):
spec = client.spec_from(server)
for entry in _offered_tools(server):
name = str(entry.get("name") or "")
offered = str(entry.get("offer_name") or "") or offer_name(
server.slug, name, taken=claimed
)
claimed.add(offered)
if not FUNCTION_NAME.match(offered):
continue
out.append(
ToolDef(
name=offered,
family=f"{FAMILY_MCP}:{server.slug}",
description=entry.get("description") or f"{name}, from {server.name}.",
parameters=entry.get("schema") or {"type": "object", "properties": {}},
run=_runner(spec, name, offered),
)
)
return out
async def refresh(db: DBSession, server: McpServer) -> tuple[int, str]:
"""Contact a server and cache what it advertises. Returns (count, error).
Shaped like `api/admin.py:_refresh_models`, including writing `last_error`
and `last_checked_at` on both paths so the row says what happened rather
than only whether it worked.
"""
spec = client.spec_from(server)
try:
advertised, info, version = await client.list_tools(spec)
except (McpError, FetchError) as exc:
server.last_error = exc.message
server.last_checked_at = datetime.now(UTC)
db.commit()
return 0, exc.message
taken: set[str] = set()
for entry in advertised:
entry["offer_name"] = offer_name(server.slug, entry["name"], taken=taken)
# Choices about tools that are still advertised survive; ones about tools
# that have gone are dropped rather than left to accumulate.
names = {entry["name"] for entry in advertised}
server.tool_overrides_json = {
name: on for name, on in (server.tool_overrides_json or {}).items() if name in names
}
server.tools_json = advertised
server.server_info = info
server.protocol_version = version
server.last_error = ""
server.last_checked_at = datetime.now(UTC)
db.commit()
log.info("mcp %s advertised %d tool(s)", server.slug, len(advertised))
return len(advertised), ""
__all__ = ["offer_name", "refresh", "tool_defs"]