Skip to content
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 18 additions & 1 deletion .github/actions/conformance/expected-failures.yml
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,24 @@
# scenarios start passing and MUST be removed from this list (the runner fails
# on stale entries), so the baseline burns down per milestone.

client: []
client:
# SEP-1932 (DPoP): the SDK's OAuth client does not implement DPoP proofs.
# These scenarios are new in the da56f663 referee pin. The entries are
# per-check (conformance #406) because both scenarios pass their
# non-DPoP checks (discovery, token acquisition, request flow) live.
- auth/dpop:sep-1932-client-token-request-proof
- auth/dpop:sep-1932-client-dpop-auth-scheme
- auth/dpop:sep-1932-client-fresh-proof
- auth/dpop-nonce:sep-1932-client-token-request-proof
- auth/dpop-nonce:sep-1932-client-dpop-auth-scheme
- auth/dpop-nonce:sep-1932-client-fresh-proof
- auth/dpop-nonce:sep-1932-client-as-nonce
- auth/dpop-nonce:sep-1932-client-rs-nonce
# Workload identity federation: the OAuth client does not implement the
# urn:ietf:params:oauth:grant-type:jwt-bearer grant (it answers with
# authorization_code). Also new in the da56f663 referee pin; per-check for
# the same reason.
- auth/wif-jwt-bearer:wif-grant-type

server:
# SEP-2663 (io.modelcontextprotocol/tasks): the SDK does not implement the
Expand Down
16 changes: 9 additions & 7 deletions .github/workflows/conformance.yml
Original file line number Diff line number Diff line change
Expand Up @@ -19,17 +19,19 @@ env:
# Bump deliberately and reconcile both
# .github/actions/conformance/expected-failures*.yml files in the same change.
#
# Temporarily pinned to the pkg.pr.new build of conformance main@4944b268
# (0.2.0-alpha.8, which includes #372: fail checks whose prerequisite is
# missing instead of skipping them) — alpha.8 is not published to npm yet.
# Pinned by commit SHA so the tarball cannot move under us;
# Temporarily pinned to the pkg.pr.new build of conformance main@da56f663,
# which includes #403 (sep-2575 checks flipped to the post-spec-#3002 shape:
# clientInfo optional on requests, serverInfo in result _meta instead of the
# discover body) and #406 (per-check expected-failures granularity) — the
# last published npm release (0.2.0-alpha.9) still enforces the pre-#3002
# shape. Pinned by commit SHA so the tarball cannot move under us;
# CONFORMANCE_PKG_SHA256 pins the bytes and the fetch-and-verify step below
# downloads, checks the digest, and repoints CONFORMANCE_PKG at the
# verified local copy. Repin to the next published @modelcontextprotocol/
# conformance release (>=0.2.0-alpha.8) once it ships, then drop
# conformance release (>=0.2.0-alpha.10) once it ships, then drop
# CONFORMANCE_PKG_SHA256 and the fetch-and-verify steps.
CONFORMANCE_PKG: "https://pkg.pr.new/@modelcontextprotocol/conformance@4944b268"
CONFORMANCE_PKG_SHA256: "0f70c035782d319d72ab427653c5275db5c50429d59fae0241a645b33aeda1a7"
CONFORMANCE_PKG: "https://pkg.pr.new/@modelcontextprotocol/conformance@da56f663"
CONFORMANCE_PKG_SHA256: "bbc94678033071df4bc9851ce2054f9dff918f4501661d1d60e2d09d8c515e6d"

jobs:
server-conformance:
Expand Down
5 changes: 4 additions & 1 deletion docs/advanced/low-level-server.md
Original file line number Diff line number Diff line change
Expand Up @@ -102,10 +102,13 @@ Call it and the result carries both representations:
"content": [{"type": "text", "text": "Found 3 books matching 'dune'."}],
"structuredContent": {"matches": 3, "query": "dune"},
"isError": false,
"resultType": "complete"
"resultType": "complete",
"_meta": {"io.modelcontextprotocol/serverInfo": {"name": "Bookshop", "version": "2.0.0"}}
}
```

The `_meta` block is the server's identity stamp: the SDK adds it to every 2026-era result, with the `version` taken from the constructor or the installed package. Pass `include_server_info=False` to the server to turn it off.

The server never compares the two fields. This SDK's `Client` does: return `structured_content` that doesn't satisfy the `output_schema` you declared and `call_tool` raises a `RuntimeError` that starts with `Invalid structured content returned by tool search_books` and goes on to quote the `jsonschema` failure. Promising a schema is cheap; keeping it is on you. The whole ladder of return types and schemas is in **[Structured Output](../servers/structured-output.md)**.

## `_meta`: for the application, not the model
Expand Down
4 changes: 2 additions & 2 deletions docs/client/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ Everything else on this page is identical across all three. Headers, subprocesse

Four read-only properties, populated the moment you enter the block:

* `client.server_info`: the server's identity. `server_info.name` here is `"Bookshop"`, `server_info.version` is whatever the server reports.
* `client.server_info`: the server's identity, or `None` for a 2026-era server that does not report one (python-sdk servers do by default). `server_info.name` here is `"Bookshop"`, `server_info.version` is whatever the server reports.
* `client.server_capabilities`: what the server can do (`tools`, `resources`, `prompts`, `completions`, ...). A capability the server doesn't have is `None`.
* `client.protocol_version`: the protocol version the two sides agreed on. Here it is `"2026-07-28"`.
* `client.instructions`: the server's `instructions=` string, or `None` if it didn't set one.
Expand Down Expand Up @@ -202,7 +202,7 @@ There is one constructor flag built for that: `Client(mcp, raise_exceptions=True
## Recap

* `Client(x)` connects in-memory to a server object, over Streamable HTTP to a URL string, and over anything else via a transport.
* `async with` is the whole lifecycle. Inside it, `server_info`, `server_capabilities`, `protocol_version` and `instructions` are already populated.
* `async with` is the whole lifecycle. Inside it, `server_capabilities` and `protocol_version` are already populated; `server_info` and `instructions` are too when the server provides them.
* `list_tools()` gives you each tool's `name`, `title`, `description` and `input_schema`.
* `call_tool()` returns `content` for the model, `structured_content` for your code, and `is_error`. A raising tool is a result, not an exception.
* `content` is a union of block types; narrow with `isinstance` before reading.
Expand Down
2 changes: 1 addition & 1 deletion docs/client/session-groups.md
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,7 @@ Run it again. `print(sorted(group.tools))` now shows both:

`connect_to_server` returns the `ClientSession` it opened. Keep it if you ever want that server gone: `await group.disconnect_from_server(session)` removes its tools, resources, and prompts from the group.

If you already hold a connected `ClientSession` (`Client.session` is one), hand it to `await group.connect_with_session(server_info, session)` instead of opening a new transport. It aggregates the same way. The group never closes a session it didn't open.
If you already hold a connected `ClientSession` (`Client.session` is one), hand it to `await group.connect_with_session(server_info, session)` instead of opening a new transport. It aggregates the same way. The group never closes a session it didn't open. `server_info` names the server for component prefixes; on a 2026-era connection `client.server_info` can be `None` (identity is optional), so pass your own `Implementation(name=..., version=...)` in that case.

## The classic handshake

Expand Down
2 changes: 2 additions & 0 deletions docs/get-started/testing.md
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,8 @@ async def client(): # (2)!
@pytest.mark.anyio
async def test_call_add_tool(client: Client):
result = await client.call_tool("add", {"a": 1, "b": 2})
# Ignore the server identity stamp in `_meta`; its `version` tracks the installed package.
result.meta = None
assert result == snapshot(
CallToolResult(
content=[TextContent(type="text", text="3")],
Expand Down
34 changes: 33 additions & 1 deletion docs/migration.md
Original file line number Diff line number Diff line change
Expand Up @@ -468,6 +468,38 @@ now a plain `dict[str, Any]`: pass a dict when constructing params
and read extras with dictionary access (`params.meta["traceparent"]`) instead of
attribute access. The JSON wire format is unchanged.

### Server identity moved from the `server/discover` result body to result `_meta`

The 2026-07-28 draft changed how identity travels
([spec #3002](https://github.com/modelcontextprotocol/modelcontextprotocol/pull/3002)):
`serverInfo` is no longer a field of the `server/discover` result. Servers now
report who they are by stamping `io.modelcontextprotocol/serverInfo` into the
`_meta` of every 2026-era result, and the request-side `clientInfo` `_meta` key
became optional (`protocolVersion` and `clientCapabilities` remain required).

What changed in the SDK:

- `DiscoverResult` no longer has a `server_info` field. Read or write identity
through result `_meta`; the key is exported as `mcp_types.SERVER_INFO_META_KEY`.
- Servers stamp `serverInfo` into every 2026-era result's `_meta` by default,
built from the constructor identity fields (`name`, `version`, `title`, and
so on). Pass `include_server_info=False` to `Server(...)` or `MCPServer(...)`
to turn it off. A `serverInfo` value your handler already set in `_meta` is
never overwritten. Handshake-era responses are unchanged, and notifications
and error responses are never stamped.
- `client.server_info` and `session.server_info` are `Implementation | None`
on 2026-era connections: identity is optional on the wire, so a server that
does not stamp it reads as `None`. Handshake-era connections still always
have it. A pinned `Client(target, mode="2026-07-28")` without
`prior_discover=` now reports `None` instead of an `Implementation` with
empty strings. The stamp is display-only in the spec, so a malformed value
from a misbehaving server also reads as `None` rather than failing the call.
- Requests that omit `clientInfo` are now accepted. On the server,
`ctx.session.client_params` is `None` for such requests; capability checks
should use `ctx.session.client_capabilities` (or `ctx.client_capabilities`
in `MCPServer` handlers), which is recorded whether or not the client
identified itself.

### `SUPPORTED_PROTOCOL_VERSIONS` deprecated; `LATEST_PROTOCOL_VERSION` changed meaning

`SUPPORTED_PROTOCOL_VERSIONS` is deprecated — it's now the union of `HANDSHAKE_PROTOCOL_VERSIONS` (initialize-handshake versions) and `MODERN_PROTOCOL_VERSIONS` (per-request-envelope versions). If you were using it to mean "versions the initialize handshake accepts", switch to `HANDSHAKE_PROTOCOL_VERSIONS`. Named scalars derived from these tuples are now exported alongside them — `LATEST_HANDSHAKE_VERSION`, `LATEST_MODERN_VERSION`, `OLDEST_SUPPORTED_VERSION` — so prefer those over indexing the tuples directly. All of these live in `mcp_types.version` (previously `mcp.shared.version`): `from mcp_types.version import HANDSHAKE_PROTOCOL_VERSIONS`.
Expand Down Expand Up @@ -1498,7 +1530,7 @@ version = session.protocol_version

The raw handshake result is also retained: `session.initialize_result` is set after `initialize()` (≤2025-11-25 servers — including `stateless_http=True` servers, which still answer `initialize`); `session.discover_result` is set after `discover()` (2026-07-28+ servers). At most one is non-`None`.

On the high-level `Client`, `client.server_capabilities`, `client.server_info`, and `client.protocol_version` are non-nullable inside the context manager. `client.instructions` remains `str | None` since the server may omit it. (The lowlevel `ClientSession` still lets you call methods before any handshake, as in v1; `Client` always connects on enter — by default it probes `server/discover` and falls back to the initialize handshake.)
On the high-level `Client`, `client.server_capabilities` and `client.protocol_version` are non-nullable inside the context manager. `client.instructions` remains `str | None` since the server may omit it, and `client.server_info` is `Implementation | None`: on 2026-era connections identity is optional wire metadata, so a server that does not report it reads as `None` (see [Server identity moved to result `_meta`](#server-identity-moved-from-the-serverdiscover-result-body-to-result-_meta)). (The lowlevel `ClientSession` still lets you call methods before any handshake, as in v1; `Client` always connects on enter — by default it probes `server/discover` and falls back to the initialize handshake.)

### `cursor` parameter removed from `ClientSession` list methods

Expand Down
10 changes: 5 additions & 5 deletions docs/protocol-versions.md
Original file line number Diff line number Diff line change
Expand Up @@ -68,10 +68,10 @@ A pin is a promise *you* make: you already know the server speaks that version.
A pin is not a discovery. Print `client.server_info` and the price is right there:

```text
name='' title=None version='' description=None website_url=None icons=None
None
```

The client never asked the server who it is, so `server_info` is a blank. `client.server_capabilities`
The client never asked the server who it is, so `server_info` is `None`. `client.server_capabilities`
is the same story: every capability is `None`. Tool calls still work (the protocol needs none of it);
code that reads `server_capabilities` to decide what to offer does not.

Expand All @@ -87,7 +87,7 @@ ValueError: mode must be 'legacy', 'auto', or one of ['2026-07-28']; got '2025-0

The probe is cheap, but it is still a round trip you pay on every reconnect, and the answer almost never changes.

So keep it. After an `auto` connection, `client.session.discover_result` holds the exact `DiscoverResult` the server sent: its `supported_versions`, its `capabilities`, its `server_info`, its `instructions`. Hand it back as `prior_discover=` the next time:
So keep it. After an `auto` connection, `client.session.discover_result` holds the exact `DiscoverResult` the server sent: its `supported_versions`, its `capabilities`, its `instructions`, and the identity the server stamped into the result's `_meta`. Hand it back as `prior_discover=` the next time:

```python title="client.py" hl_lines="15 17"
--8<-- "docs_src/protocol_versions/tutorial004.py"
Expand All @@ -112,7 +112,7 @@ The second connection made **zero** negotiation round trips and still knows exac
| --- | --- | --- |
| `Client(target)` | one `server/discover` probe; the `initialize` handshake if it fails | the newest version both sides speak, whichever era |
| `Client(target, mode="legacy")` | the `initialize` handshake | a handshake-era version; server-initiated requests work |
| `Client(target, mode="2026-07-28")` | none | that version, pinned, with a blank `server_info` |
| `Client(target, mode="2026-07-28")` | none | that version, pinned, with `server_info` as `None` |
| `Client(target, mode="2026-07-28", prior_discover=saved)` | none | that version, pinned, *and* the identity you saved last time |

## Recap
Expand All @@ -121,7 +121,7 @@ The second connection made **zero** negotiation round trips and still knows exac
* `mode="auto"` is the default: probe, fall back. Leave it alone unless one of the other three rows describes you.
* `client.protocol_version` is always the answer to "what did I get?".
* `mode="legacy"` forces the handshake. It is what you need for server-initiated requests: sampling, push elicitation, `message_handler`.
* A version pin (`mode="2026-07-28"`) sends no negotiation traffic at all, at the cost of a blank `server_info`.
* A version pin (`mode="2026-07-28"`) sends no negotiation traffic at all, at the cost of `client.server_info` being `None`.
* `prior_discover=` pays that cost back: save `client.session.discover_result`, reconnect with it, get both.

A modern connection has no push channel, so how does a 2026 server ask you a question mid-call? It returns it: **[Multi-round-trip requests](handlers/multi-round-trip.md)**.
3 changes: 2 additions & 1 deletion docs/servers/media.md
Original file line number Diff line number Diff line change
Expand Up @@ -97,9 +97,10 @@ The same `icons=[...]` keyword is accepted by `MCPServer(...)`, `@mcp.tool()`, `

### Where a client sees them

Icons travel with whatever they decorate. The server's arrive when the client connects, on `client.server_info`:
Icons travel with whatever they decorate. The server's arrive when the client connects, on `client.server_info` (optional on 2026-era connections, so narrow it first):

```python
assert client.server_info is not None # python-sdk servers identify themselves by default
client.server_info.icons # [Icon(src="https://example.com/brand-kit.png", mime_type="image/png", sizes=["48x48"])]
```

Expand Down
1 change: 1 addition & 0 deletions docs/whats-new.md
Original file line number Diff line number Diff line change
Expand Up @@ -197,6 +197,7 @@ At 2026-07-28 the standalone HTTP GET stream and `resources/subscribe` are repla

### The rest, quickly

* **Identity is optional, per-message metadata.** The request-side `clientInfo` `_meta` key is optional (the required pair is `protocolVersion` + `clientCapabilities`), and `serverInfo` moved out of the `server/discover` result body: servers stamp it into every 2026-era result's `_meta` instead (since `2.0.0b3`; [spec #3002](https://github.com/modelcontextprotocol/modelcontextprotocol/pull/3002)). The SDK stamps by default and `include_server_info=False` turns it off; `client.server_info` is `None` when a server chooses not to identify itself. The **[Migration Guide](migration.md#server-identity-moved-from-the-serverdiscover-result-body-to-result-_meta)** has the details.
* **Requests are routable without parsing bodies.** Modern HTTP requests carry `Mcp-Method` (and, for the three tool-ish calls, `Mcp-Name`); a tool input-schema property annotated with `x-mcp-header` is mirrored into an `Mcp-Param-*` header and cross-checked by the server ([SEP-2243](https://github.com/modelcontextprotocol/modelcontextprotocol/pull/2243)). Gateways and rate limiters can route on headers alone; the **[Migration Guide](migration.md#servers-validate-mcp-param-headers-against-the-request-body-sep-2243)** has the rules.
* **Results carry cache hints.** List and read results declare `ttlMs` and `cacheScope` ([SEP-2549](https://github.com/modelcontextprotocol/modelcontextprotocol/pull/2549)); you set them per method with `cache_hints=`, and `Client` honors them with a built-in response cache. A server that sends no hints (every pre-2026 server) sees identical, uncached traffic. **[Caching hints](client/caching.md)**.
* **Extensions are first class.** Servers and clients declare optional capability bundles under reverse-DNS identifiers ([SEP-2133](https://github.com/modelcontextprotocol/modelcontextprotocol/pull/2133)); the built-in `Apps` extension (MCP Apps) is the reference. **[Extensions](advanced/extensions.md)** and **[MCP Apps](advanced/apps.md)**.
Expand Down
3 changes: 2 additions & 1 deletion docs_src/protocol_versions/tutorial004.py
Original file line number Diff line number Diff line change
Expand Up @@ -16,4 +16,5 @@ async def main() -> None:

async with Client(mcp, mode="2026-07-28", prior_discover=saved) as client:
print(client.protocol_version)
print(client.server_info.name)
if client.server_info is not None:
print(client.server_info.name)
Original file line number Diff line number Diff line change
Expand Up @@ -357,13 +357,13 @@ async def test_missing_capability(ctx: Context) -> str:
``CallToolResult.isError``) so the conformance harness observes a protocol-level
error response with ``data.requiredCapabilities``.
"""
client_params = ctx.session.client_params
sampling_declared = client_params is not None and client_params.capabilities.sampling is not None
capabilities = ctx.session.client_capabilities
sampling_declared = capabilities is not None and capabilities.sampling is not None
if not sampling_declared:
raise MCPError(
code=MISSING_REQUIRED_CLIENT_CAPABILITY,
message="This tool requires the client 'sampling' capability",
data={"requiredCapabilities": ["sampling"]},
data={"requiredCapabilities": {"sampling": {}}},
)
return "Client declared sampling capability; proceeding."

Expand Down
2 changes: 1 addition & 1 deletion examples/stories/_harness.py
Original file line number Diff line number Diff line change
Expand Up @@ -162,7 +162,7 @@ def run_client(main: Callable[..., Awaitable[None]]) -> None:
if cfg["era"] == "dual-in-body":
# The story pins its connection modes inside ``main`` itself, so hand it "auto"
# (the ``Client`` default) and let those in-body pins decide. A hard version pin
# here would skip the discover probe and leave ``server_info`` blank.
# here would skip the discover probe and leave `server_info` None.
era = "in-body"
mode = {"modern": LATEST_MODERN_VERSION, "legacy": "legacy", "in-body": "auto"}[era]

Expand Down
4 changes: 3 additions & 1 deletion examples/stories/dual_era/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,9 @@ leg fails there today — run over `--http`.
at construction; no date strings appear in the body.
- `client.py` — `client.protocol_version` / `client.server_info` /
`client.server_capabilities` are era-neutral: populated by `initialize` *or*
`server/discover`, whichever ran.
`server/discover`, whichever ran. On the 2026 era `server_info` comes from
the optional `serverInfo` `_meta` stamp (`None` for a server that does not
identify itself); `initialize` always carries it.
- `server.py` — `ctx.request_context.protocol_version` is the era branch key
(lowlevel: `ctx.protocol_version` directly). Compare against
`MODERN_PROTOCOL_VERSIONS`, never a date literal.
Expand Down
Loading
Loading