litellm/litellm
Sameer Kankute 68efe6970c
fix(mcp): JWT on tools/list and REST tools/call server resolution (#28227)
* fix(mcp): JWT on tools/list, REST server_id resolution, tool_server_mismatch

Sign outbound MCP JWTs for list_mcp_tools and inject headers on the tools/list
path. Resolve server_id on /mcp-rest/tools/call and return 403 tool_server_mismatch
when the tool does not belong to the requested server. Default missing arguments to {}.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(mcp): restrict list JWTs to mcp:tools/list and default REST arguments to {}

- List-only JWTs (call_type=list_mcp_tools) no longer carry the broad
  mcp:tools/call scope. _build_scope() now emits only mcp:tools/list
  when no tool name is provided, mirroring the existing least-privilege
  rule that tool-call JWTs omit mcp:tools/list.
- REST /tools/call now defaults a missing 'arguments' field to {} so
  execute_mcp_tool() and downstream **arguments / .keys() calls don't
  receive None and crash with TypeError/AttributeError.

Co-authored-by: Yassin Kortam <yassin@berri.ai>

* fix(mcp): validate tool/server in call_tool; skip JWT signer when not configured or static auth present

Co-authored-by: Yassin Kortam <yassin@berri.ai>

* fix(mcp): align tests and mypy with user_api_key_auth on tools/list

Update mocks for the new _get_tools_from_server parameter, mock server
registry in REST access-denied test, and narrow static_headers for mypy.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(test): accept user_api_key_auth in get_tools_from_mcp_servers mock

The side_effect for the all-servers case did not accept the new kwarg,
so tools/list returned an empty list.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(mcp): fail fast for unknown tools when server mapping exists

Server-name fallback in call_tool must not open an upstream session when
the tool is absent from a populated mapping. Update the HTTP transport test
to register a known tool before asserting not-found behavior.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix mypy

* Fix mypy

* fix(mcp): preserve tools/call scope on missing tool name; pass user_api_key_auth in list_tools

Co-authored-by: Yassin Kortam <yassin@berri.ai>

* fix(mcp): match alias/server_name in _resolve_mcp_server_for_tool_call

The registry lookup in _resolve_mcp_server_for_tool_call previously only
compared candidate.name against the provided server_name, but tool name
prefixes can be derived from a server's alias or server_name (see
get_server_prefix). When the tool→server mapping is empty/stale (cold
start, dynamic tools), the lookup would fail for alias-configured
servers even though get_mcp_server_by_name (used by the REST path)
matches alias, server_name, and name.

Match the same priority of identifiers in both the registry pass and
the unprefixed fallback so the MCP protocol call_tool path is
consistent with the REST path.

Co-authored-by: Yassin Kortam <yassin@berri.ai>

* fix(mcp): reuse proxy_logging DualCache in inject_mcp_jwt_headers_for_upstream

Instead of allocating a fresh DualCache() on every tools/list invocation,
prefer the shared proxy_logging_obj.internal_usage_cache.dual_cache when
available. The cache argument is currently unused by MCPJWTSigner, but
sharing the proxy's cache avoids per-call allocation overhead and matches
the cache identity used elsewhere in the proxy hook plumbing — so any
future per-request state stored in cache will survive across list calls.

Co-authored-by: Claude <noreply@anthropic.com>

* fix(mcp): return 403 ip_filtering for IP-restricted servers in tools/call name lookup

Co-authored-by: Yassin Kortam <yassin@berri.ai>

* fix(test): accept user_api_key_auth kwarg in list_tools mocks

The proxy-infra job was failing on four TestMCPServerManager tests because
the mock_get_tools_from_server stubs did not accept the new
user_api_key_auth keyword argument that list_tools now forwards to
_get_tools_from_server. Add the kwarg to each stub so list_tools can call
through cleanly.

Co-authored-by: Claude <claude@anthropic.com>

* fix(mcp): skip JWT injection when per-user mcp_auth_header is set

MCPClient._get_auth_headers() applies extra_headers AFTER writing
Authorization from auth_value, so an injected JWT silently overwrites
the user's per-server OAuth token. Guard the JWT signer with
'not mcp_auth_header' so per-user OAuth (and any dict-form per-user
auth) takes precedence, mirroring the existing static_headers guard.

Adds a regression test that the signer's inject helper is not called
when mcp_auth_header is supplied.

* fix(mcp): skip JWT injection when extra_headers already has Authorization

When a server uses per-user OAuth tokens, the resolved token is passed
into _get_tools_from_server via extra_headers. The JWT injection guard
only checked mcp_auth_header and the server's static headers, so the
signer would silently overwrite the user's OAuth Authorization header.

Add a check for an existing Authorization entry in extra_headers so
caller-supplied per-user OAuth tokens take precedence over JWT signing.

Co-authored-by: Yassin Kortam <yassin@berri.ai>

* test(mcp): cover JWT signer + tool-call resolution branches

Adds unit tests for the new MCPServerManager helpers (_resolve_mcp_server_for_tool_call,
_resolve_oauth2_headers_for_tool_call) and the new MCPJWTSigner paths
(_build_scope call_type branches and inject_mcp_jwt_headers_for_upstream).
Brings patch coverage above the auto target without changing behavior.

Co-authored-by: Claude <claude@anthropic.com>

* fix(mcp): retry tool-server lookup with prefixed name in REST mismatch check

When the REST /mcp-rest/tools/call path sends a raw tool name plus
requested_server_id, _get_mcp_server_from_tool_name(name) can return
None if the mapping only stores the prefixed form. That bypassed the
tool_server_mismatch 403 guard and let the call fall through to
trusting requested_server.

Retry the lookup with every known prefix of the requested server so
the mismatch check fires whenever the tool is actually registered.

Co-authored-by: Yassin Kortam <yassin@berri.ai>

* fix(mcp): always reject unknown tools in server-name fallback

Defense-in-depth: _resolve_mcp_server_for_tool_call previously skipped
the unknown-tool check whenever the per-server mapping had no entries
yet (cold start, OAuth2 lazy listing, or upstream listing failure),
allowing arbitrary tool names to reach upstream servers.

Tighten the check so the server-name fallback always rejects tool
names not present in the mapping. Callers must call list_tools first
(standard MCP flow) before tools/call can resolve. Removes the
now-unused _mapping_has_tools_for_server helper and adds an
explicit empty-mapping rejection test alongside the existing
populated-mapping rejection test.

Co-authored-by: Sameer Kankute <sameer@berri.ai>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Yassin Kortam <yassin@berri.ai>
Co-authored-by: Claude <claude@anthropic.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Claude (greptile subagent) <claude-greptile-bot@anthropic.com>
2026-05-20 13:31:44 -07:00
..
a2a_protocol feat(guardrails): LLM-as-a-Judge guardrail (#26360) 2026-04-24 17:15:32 -07:00
anthropic_interface style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
assistants
batch_completion
batches fix(vertex-ai): fix zero cost/usage on completed Vertex AI batch jobs (#27912) 2026-05-15 04:47:02 -07:00
caching fix(caching): replay openai/responses bridge cache hits as chat streams (#28158) 2026-05-18 16:27:06 -07:00
completion_extras fix(caching): replay openai/responses bridge cache hits as chat streams (#28158) 2026-05-18 16:27:06 -07:00
compression Prompt Compression - add it to the proxy (#25729) 2026-04-20 15:08:00 -07:00
containers style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
endpoints/speech/speech_to_completion_bridge
evals style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
experimental_mcp_client feat(mcp): add OBO MCP Auth (#27421) 2026-05-07 15:35:21 -07:00
files thread trusted params through vertex file content 2026-05-01 18:24:22 -07:00
fine_tuning address greptile review feedback (greploop iteration 1) 2026-03-27 20:04:41 +05:30
google_genai feat(proxy): LiteLLM headers on Google native generateContent routes (#25500) 2026-04-29 12:34:14 -07:00
images Feat(dashscope): add image generation support for qwen-image-2.0 and qwen-image-2.0-pro (#25672) 2026-04-22 20:03:46 -07:00
integrations feat: propagate team_id and team_alias to all child OTEL spans (#28273) 2026-05-19 15:31:25 -07:00
interactions Gemini managed agents support (#28270) 2026-05-19 16:02:03 -07:00
litellm_core_utils Day 0 support : Gemini 3.5 Flash (#28268) 2026-05-19 15:50:54 -07:00
llms fix(router): use forwarded model_id for native Azure container IDs (#27921) 2026-05-20 12:32:34 -07:00
ocr chore: reject bare str at file-input sinks to prevent local-file read (#27762) 2026-05-12 16:40:07 -07:00
passthrough fix(passthrough): log when streaming spend-tracking flush fails to schedule 2026-04-30 02:39:29 +00:00
proxy fix(mcp): JWT on tools/list and REST tools/call server resolution (#28227) 2026-05-20 13:31:44 -07:00
proxy_auth
rag style: black formatting 2026-04-25 14:47:54 -07:00
realtime_api
rerank_api Fix review 2026-04-30 09:10:24 +05:30
responses fix(responses): preserve cache_control in Responses API -> Chat Completion transformation (#27727) 2026-05-13 12:17:06 -07:00
router_strategy feat: add weighted-routing failover (#27980) 2026-05-15 17:28:54 +00:00
router_utils fix(responses): register cooldowns on failure + fail fast on stale encrypted_content (#27820) 2026-05-13 09:03:13 -07:00
search style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
secret_managers Implement normalize_nonempty_secret_str function to trim whitespace from secrets and treat empty values as unset. Update proxy_server to use this function for Grafana credentials. Enhance tests to validate the new normalization behavior. 2026-05-04 18:17:31 +00:00
skills chore(proxy): scope skills and container resources 2026-04-30 18:23:58 -07:00
types Gemini managed agents support (#28270) 2026-05-19 16:02:03 -07:00
vector_store_files
vector_stores chore(vector stores): tighten managed store access 2026-04-30 15:04:25 -07:00
videos style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
__init__.py Gemini managed agents support (#28270) 2026-05-19 16:02:03 -07:00
_internal_context.py fix(proxy): harden request parameter handling 2026-04-16 01:38:12 +00:00
_lazy_imports.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
_lazy_imports_registry.py fix(utils): import get_secret at runtime (#28014) 2026-05-15 14:01:18 -07:00
_logging.py fix(bedrock-mantle): use /anthropic/v1/messages path for Mantle endpo… (#27976) 2026-05-15 13:31:59 -07:00
_redis.py Litellm oss staging (#28161) 2026-05-18 16:27:44 -07:00
_redis_credential_provider.py feat: add ability to auth to azure with token (#27556) 2026-05-09 22:34:09 +00:00
_service_logger.py
_uuid.py
_version.py
anthropic_beta_headers_config.json fix(anthropic,bedrock,databricks): four reasoning_effort follow-ups 2026-05-03 10:03:53 -07:00
anthropic_beta_headers_manager.py
blog_posts.json
budget_manager.py docs(budget_manager): add docstring to BudgetManager.reset_cost (#27867) 2026-05-13 13:28:22 -07:00
constants.py feat(mcp): support MCP access group names in URL-based namespacing (#27726) 2026-05-13 20:20:38 -07:00
cost.json
cost_calculator.py Litellm oss staging (#28161) 2026-05-18 16:27:44 -07:00
exceptions.py Litellm oss staging (#28161) 2026-05-18 16:27:44 -07:00
main.py Litellm oss staging (#28161) 2026-05-18 16:27:44 -07:00
model_prices_and_context_window_backup.json feat(gemini): add gemini-3.1-flash-lite model cost map (#28320) 2026-05-20 10:03:14 -07:00
mypy.ini
policy_templates_backup.json
provider_endpoints_support_backup.json Feature/add audio support for scaleway (#26110) 2026-04-20 14:49:41 -07:00
py.typed
router.py fix(router): use forwarded model_id for native Azure container IDs (#27921) 2026-05-20 12:32:34 -07:00
scheduler.py
setup_wizard.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
timeout.py docs: add class docstring to _LoopWrapper (#27870) 2026-05-13 13:54:00 -07:00
utils.py fix(deepseek): use native /anthropic/v1/messages endpoint and sanitize tools (#28200) 2026-05-18 18:14:13 -07:00