Commit Graph

37 Commits (de2dfd3034a7b506fa269910401bbdcbd4efc71d)

Author SHA1 Message Date
KennySimpson 69a7fd9931
fix(mcp): close legacy chat responses on HTTP errors (#3930) 2026-10-08 01:25:18 +08:00
wxggzz 273db881c6 fix(mcp): assemble multiline SSE events before parsing 2026-09-22 20:09:02 +08:00
lyingbug 76a19f14c4
feat(mcp): add built-in MCP server with per-workspace endpoints (#3371)
* feat(mcp): add built-in MCP server with per-workspace endpoints

WeKnora previously exposed itself to MCP clients only through the Python
package under mcp-server/, which binds one process to one API key and
therefore to one workspace, and mirrors the REST API tool-for-tool.

This adds a native MCP server surface to the Go backend:

- New mcp_endpoints table (PostgreSQL 000100, SQLite 000020). A workspace
  can publish any number of endpoints, each with its own bearer token
  (SHA-256 stored, rotatable, shown once), knowledge-base allowlist, tool
  allowlist, default agent and per-minute rate limit.
- Management API under /api/v1/mcp-endpoints (Viewer reads, Admin writes,
  API keys need manage_channels) plus a tool catalog endpoint.
- internal/mcpserver hosts one mcp-go Streamable HTTP server in stateless
  mode at /mcp/:endpoint_id. tools/list is filtered per endpoint and
  tools/call re-checks the allowlist, applies rate limiting and touches
  last_used_at. MCPEndpointAuth resolves the token and injects the
  workspace, an mcp_endpoint principal and an API-key style scope derived
  from the endpoint, so existing knowledge-base and capability checks
  apply unchanged.
- Redesigned tool set (12 tools in four groups): retrieval and reading
  reuse the agent's native tools; ask runs the default or a named agent
  synchronously and returns a cited answer with a session_id for
  follow-ups; wiki tools cover search, read and index; write tools are
  off by default. Knowledge bases accept ids or names.
- Frontend: new "MCP Server" integrations tab (tab id mcpserver, to
  avoid clashing with the existing MCP-client settings section) with
  endpoint cards, a create/edit drawer, a one-time token dialog and
  ready-to-paste snippets for Cursor/VS Code/Claude Desktop, Claude Code
  and mcp-remote. Locales updated in all five languages.
- Deployment capability integrations.mcpserver wired on both sides.
- Docs: website-docs MCP page now leads with the built-in server; the
  Python mcp-server README carries a deprecation notice.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* fix(mcp): wire the MCP server into DI/router and tighten authorization

The previous commit lost eight staged files to the repo pre-commit hook,
which resolves ROOT to the main checkout and re-adds the main-checkout
copies of tracked files into the worktree index. This commit restores them
(container providers, RouterParams and route registration, context key,
principal, clone table entry, deployment capability key, SQLite parity
test) and addresses the review findings:

- Knowledge-base scope is authorized, not trusted: endpoint allowlists and
  every tool call resolve each knowledge base through access.ResolveKB for
  the calling principal (ownership or organization share). Foreign IDs are
  rejected on create/update and dropped at call time.
- Write tools mint explicit editor grants via access.KBAccess.WithGrant
  before calling the knowledge service, so add/update/delete go through the
  same RequireKBWrite path as the REST API. add_document also checks the
  grant itself.
- ask no longer accepts agent_id. It runs only the endpoint's configured
  agent; tenant-owned agents and user-facing builtins qualify, internal
  builtins (wiki fixer, skill installer) are refused both on save and at
  call time. Web search is forced off for MCP calls.
- Tool annotations match behaviour: ask is not read-only, add_document is
  a mutation.
- CORS allows MCP-Protocol-Version / Mcp-Session-Id / Last-Event-ID and
  exposes Mcp-Session-Id for browser-based MCP clients.
- Rate limiter runs its local cleanup goroutine; SQLite migration gains the
  deleted_at index for parity with PostgreSQL; non-ASCII endpoint names get
  unique mcpServers keys derived from the endpoint id.
- Swagger annotations on the management handler.
- Tests: KB isolation (service and server), write grants, endpoint-agent
  restriction, tool annotations, and a router test that mounts the public
  /mcp/:endpoint_id surface and checks the deployment capability.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* chore(mcp): renumber migrations after rebase onto main

main took 000100 / 000020 for chunks_index_diet, so the mcp_endpoints
migrations move to 000101 (PostgreSQL) and 000021 (SQLite); the SQLite
parity test and docs follow.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* fix(mcp): run document tools under the knowledge base owner tenant

Shared knowledge bases resolved through access.ResolveKB were only half
usable: documents of an organization-shared knowledge base are stored under
the owner tenant, so the document-level tools that queried by the calling
tenant found nothing, and add_document would have created rows under the
caller's tenant inside someone else's knowledge base.

- knowledgeInScope loads documents tenant-agnostically and then requires
  the document to belong to an allowed knowledge base and to that base's
  tenant.
- scopedKBContext replaces grantContext: it resolves the grant, switches
  the execution tenant to the knowledge base owner (KBAccess.Context) and
  swaps TenantInfo to the owner so storage/model settings resolve there.
  list_documents, read_document and every write tool run under it.
- Locale text and docs no longer claim clients can pass agent_id.
- Go SDK gains MCP endpoint methods (client/mcp_endpoint.go) with docs, and
  the Swagger artifacts are regenerated.
- Tests: shared knowledge base read/write under the owner tenant, spoofed
  document tenant rejected, viewer share cannot write.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* chore(mcp): renumber migrations after rebase onto main

main now carries 000101 / 000021 (knowledge_profiles), so the
mcp_endpoints migrations move to 000102 (PostgreSQL) and 000022 (SQLite);
the SQLite parity test expects version 22 and the docs follow.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* fix(mcp): guard last_used touch without a repository and wrap SDK line

The transport tests build the server without a repository; the background
last_used_at write then dereferenced a nil interface and, on the slower CI
runner, took the test binary down. touchLastUsed now returns early when no
repository is wired, and the tests inject a recording repository and assert
the touch instead. Also wraps a 123-column SDK signature for the client
module's lll check.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-17 22:40:05 +08:00
lyingbug d7ccd5ba51
fix: align client sessions and integration request handling (#3305)
* fix: align client sessions and integration request handling

* fix: preserve trusted Doris redirects and prepare browser tests

* fix: align proxy address checks and integration test coverage
2026-09-16 16:20:57 +08:00
zhao0335 1ef38fdb8b feat(mcp): pass fileName and folder filters to knowledge APIs
create_knowledge_from_file never sent fileName, so MCP uploads always
landed in the knowledge-base root even though the backend has accepted
path-qualified names (folder_path + display name) since v0.7.2.

list_knowledge also dropped folder_path / folder_scope query params that
the REST list endpoint already supports.

Fixes #3173
2026-09-14 22:20:25 +08:00
十三分之五六七 f7cc5969e3 feat(mcp): add manual knowledge update tool 2026-09-07 14:40:33 +08:00
01luyicheng 17372215a2 docs(mcp-server): document create_knowledge_from_file/text tools
List create_knowledge_from_file (previously missing from the README tool
list) and the new create_knowledge_from_text in README.md and EXAMPLES.md,
and add a CHANGELOG entry under Unreleased.
2026-08-05 19:25:25 +08:00
01luyicheng 54c4309c65 feat(mcp-server): add create_knowledge_from_text tool
Add an MCP tool that creates a knowledge entry from raw Markdown text by
calling the existing backend endpoint
POST /knowledge-bases/{id}/knowledge/manual (handler.CreateManualKnowledge).
This completes the "text" half of #323, whose "file" half was already
covered by create_knowledge_from_file.

The tool defaults to status="publish" so the created entry is chunked,
embedded and made searchable immediately — matching the API/MCP use case
where there is no UI to publish a draft. Callers may pass status="draft"
to save without indexing.

- New client method WeKnoraClient.create_knowledge_from_text.
- New @mcp.tool() create_knowledge_from_text, resolving kb_id by name or
  UUID (consistent with create_session / hybrid_search).
- Add focused unittests verifying endpoint, request body shape, status
  default/override, and kb_id resolution wiring.
- Bump the stdio tools-list count assertion in test_mcp_transports.py
  from 29 to 30 for the newly registered tool.
2026-08-05 19:25:25 +08:00
wizardchen a8cf3a2b09 fix(mcp-server): normalize shared KB list shape for name resolution
GET /shared-knowledge-bases returns rows with nested knowledge_base
(sharedKBRow), unlike GET /knowledge-bases which returns flat KB objects.
resolve_kb_id and agent_chat preflight were reading top-level id/name,
so shared KB names never matched. Add _normalize_kb_entries and tests.
2026-08-03 15:50:33 +08:00
FincherYuan 1e75a34300 test(mcp-server): bump tool count assertion to 29 for new shared-KB tool
Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-03 15:50:33 +08:00
FincherYuan 71bdecf873 fix(mcp-server): integrate shared KBs into name resolution and tool hints
resolve_kb_id now searches both own and shared knowledge bases when
resolving a name to UUID. Error messages and docstrings in hybrid_search,
chat, and agent_chat now reference list_shared_knowledge_bases as well.

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-03 15:50:33 +08:00
FincherYuan 5f4464db8d feat(mcp-server): add list_shared_knowledge_bases tool
Add a new MCP tool to list knowledge bases shared from other workspaces
via the GET /shared-knowledge-bases endpoint, which was previously not
exposed through the MCP server.

- Add WeKnoraClient.list_shared_knowledge_bases() method
- Register list_shared_knowledge_bases() as an @mcp.tool()

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-03 15:50:33 +08:00
“ZhuangShiHao1207” b67ed27e1d fix(mcp): resolve non-UUID agent IDs 2026-07-30 17:34:37 +08:00
wizardchen 0bf9286a2e test(mcp-server): keep thread-local sessions alive 2026-07-30 17:32:44 +08:00
wizardchen a76c6ef24e fix(mcp-server): adopt official PyPI package tencent-weknora-mcp [v1.1.1]
Rename the distribution to tencent-weknora-mcp, point metadata at
Tencent/WeKnora, bump to 1.1.1 for the transport/session fixes, and
tighten publish to main/tags only via Trusted Publishing.
2026-07-30 15:52:28 +08:00
wizardchen 1e12361cb8 fix(mcp-server): restore HTTP/SSE transport compat after MCPServer migration
Keep stateless HTTP and /sse/messages/ paths aligned with pre-2.x behavior,
use thread-local requests.Session for concurrent tool handlers, and add
transport regression tests.
2026-07-30 15:52:28 +08:00
veater 37837c00a9 fix(mcp-server): migrate to MCPServer high-level API (mcp 2.x) [v1.1.0]
MCP Python SDK 2.0 removed the low-level Server decorator API
(@app.list_tools() / @app.call_tool() / app.get_capabilities()), so the
server crashed at startup with:
  AttributeError: 'Server' object has no attribute 'list_tools'

The released PyPI package weknora-mcp==1.0.1 declared 'mcp>=1.0.0' with
no upper bound, so uvx resolved to the latest 2.0.0 and the plugin's
weknora MCP server could no longer connect.

Fix: rewrite the server on top of the mcp 2.x high-level MCPServer API
(formerly FastMCP), and cap the dependency at 'mcp>=2,<3'.

- weknora_mcp_server.py: replace @app.list_tools()/@app.call_tool() with
  28 @mcp.tool() function-signature tools (input schema auto-generated
  from type hints, descriptions from docstrings, plain return values
  serialized by the framework). Transports use run_stdio_async() /
  sse_app() / streamable_http_app(). WeKnoraClient business logic is
  unchanged.
- deps: mcp>=2,<3 in pyproject.toml / requirements.txt / setup.py;
  commit uv.lock pinning mcp 2.0.0.
- version bump to 1.1.0 (pyproject, setup, __init__, main --version,
  server_version).
- check_imports.py: validate MCPServer / ToolError / mcp_types imports.
- ci(.github/workflows/mcp-server.yml): publish on merge to main +
  manual dispatch, not only on tags; add PyPI version-dedup check so
  re-runs on an unchanged version stay green (absorbed from PR #2399).

Verified: stdio initialize + tools/list returns all 28 tools; no
list_tools AttributeError; tool dispatch + error wrapping confirmed.

Co-authored-by: wizardchen <wizardchen@tencent.com>
2026-07-30 15:52:28 +08:00
wizardchen 55840b1a02 test(mcp-server): restore unittest coverage after workflow dedup
Convert test_module.py to unittest.TestCase so mcp-server.yml's
unittest discover picks up integration checks. Rename test_imports.py
to check_imports.py to keep manual diagnostics out of discovery.
2026-07-29 19:51:47 +08:00
wizardchen 4f7a36c7e6 fix(mcp-server): pin MCP Python SDK to v1.x
WeKnora MCP Server still uses v1 low-level Server decorators such as
@app.list_tools(). MCP SDK 2.0 removed those APIs, so fresh installs
could fail at startup with AttributeError. Cap the dependency at <2 and
require >=1.28 for Streamable HTTP transport support.
2026-07-29 15:43:45 +08:00
annopick 400bbbf717
fix(mcp-server): route diagnostics to stderr to fix stdio protocol crash (#2371)
* fix(mcp-server): route diagnostics to stderr to fix stdio protocol crash

Entry scripts (run_server.py, main.py, run.py) printed diagnostics to
stdout via bare print(). Under the stdio transport (the default and the
path used by all MCP clients per MCP_CONFIG.md: `uv run run_server.py`),
stdout is the JSON-RPC channel, so the plain-text lines emitted before
the initialize handshake corrupted the protocol stream. Strict MCP clients
(Claude Desktop / Cursor / ZCode / VS Code Copilot) treated this as a
fatal protocol error and reported the server as failed-to-start.

Redirect all diagnostic print() to sys.stderr (per MCP spec, only
JSON-RPC may use stdout). weknora_mcp_server.py already routes through
logging (stderr) and is unchanged.

Verified against a live backend (initialize -> tools/list (28 tools) ->
tools/call list_knowledge_bases); stdout first byte is now '{' with all
diagnostics on stderr.

* chore(mcp-server): publish package name as weknora-mcp

Rename the PyPI distribution name from weknora-mcp-server to weknora-mcp
(tools used: pyproject [project].name + setup.py name). The installed
console-script commands (weknora-mcp-server, weknora-server) and the
Python module (weknora_mcp_server) are unchanged for backward compatibility.

* fix(mcp-server): include upload_paths in wheel + bump to 1.0.1

The 1.0.0 wheel was missing upload_paths.py: it was absent from the
[tool.setuptools] py-modules list (and setup.py py_modules), so setuptools
never packed it. weknora_mcp_server.py line 26 does
`from upload_paths import resolve_upload_file_path, set_active_transport`,
so any path that fully imports the module — i.e. the MCP client initialize
handshake — crashed with ModuleNotFoundError. `--version` survived only
because argparse exits before that import runs.

Fix: add 'upload_paths' to py-modules (pyproject.toml + setup.py) and bump
to 1.0.1 (1.0.0 is immutable on PyPI). Also sync the user-facing version
strings (__version__, server_version, main --version) to 1.0.1.

* ci(mcp-server): add workflow.yml to build & publish to PyPI via OIDC

Adds .github/workflows/workflow.yml adapted from annopick/tuomin's ci.yml:
- test: matrix Python 3.10–3.13 (matches requires-python >=3.10), runs the
  flat test_*.py suite in mcp-server/
- build: on mcp-server-v* tags, builds sdist + wheel via uv build, and
  guards against the 1.0.0 regression by asserting upload_paths.py is in
  the wheel before publishing
- publish: PyPI Trusted Publishing (OIDC, id-token: write) to weknora-mcp,
  no API token needed

Publishing is gated on tags named mcp-server-v* to decouple from the Go
release workflow that already targets v* tags.

* fix(mcp-server): route diagnostics to stderr and fix packaging/CI

Prevent MCP stdio startup crashes by sending entry-script diagnostics to
stderr, package upload_paths in the wheel, and add unittest-based CI with
stdout purity regression tests.

---------

Co-authored-by: wizardchen <wizardchen@tencent.com>
2026-07-28 21:23:09 +08:00
FincherYuan 0f8232b7eb fix(mcp-server): correct SSE message route to prevent initialization timeout
The SSE transport's POST handler was mounted at /messages/, but the
SseServerTransport SDK prepends the Starlette root_path ("/sse") to
the endpoint parameter, instructing clients to POST to /sse/messages/.
This path mismatch caused MCP initialization requests to never reach
the handler, resulting in a 60s+ timeout on connect.

Fix: move the Mount to /sse/messages/ and place it before the /sse
catch-all route, since Starlette's Mount uses prefix matching and
/sse would otherwise intercept /sse/messages/ requests.
2026-07-28 20:34:56 +08:00
wizardchen 380e371c2e refactor: remove Neo4j-based conversation memory feature
Drop the memory pipeline, API fields, settings UI, and embed toggles so chat no longer depends on Neo4j graph storage for episodic recall.
2026-07-18 23:41:48 +08:00
wizardchen 41975abcc5 refactor(terminology): rename user-facing tenant labels to workspace
Align product copy, API docs, Swagger descriptions, and i18n strings
with workspace terminology while keeping internal tenant identifiers
and headers unchanged for API compatibility.
2026-07-14 16:14:43 +08:00
wizardchen 26cc335420 fix(security): apply MCP upload sandbox when transport is set via CLI
Record the active transport at run_stdio/run_sse/run_http startup so
create_knowledge_from_file path checks apply even when MCP_TRANSPORT
is not set in the environment.
2026-07-02 17:08:17 +08:00
wizardchen 040504447e fix(security): block refresh tokens as bearer and sandbox MCP uploads
Reject refresh JWTs in ValidateToken, revoke all user sessions on logout,
and restrict create_knowledge_from_file to allowed directories on network MCP transports.
2026-07-02 17:08:17 +08:00
wizardchen cd65665894 fix(security): close remaining GHSA gaps from security triage
Block scheme-prefixed loopback storage checks, validate Notion attachment
URLs, sanitize wiki markdown HTML, and require MCP_SERVER_AUTH_TOKEN for
network MCP transports.
2026-07-02 15:03:53 +08:00
wizardchen abf6a99b90 fix(api): add POST for hybrid-search while keeping GET compatibility (#1727)
GET with a JSON body was non-standard and confused integrators. Register
POST as the preferred method and keep GET for existing clients; update SDK,
MCP server, and API docs accordingly.

Refs: https://github.com/Tencent/WeKnora/issues/1727
2026-06-22 17:22:35 +08:00
mileslai b603b1dcfa fix(mcp-server): address Copilot PR review comments
- SSL verification now defaults to enabled; set WEKNORA_VERIFY_SSL=false to
  opt out (with a logged warning). Fixes MITM risk from default-off TLS.
- WEKNORA_CHAT_TIMEOUT parse is now guarded with try/except ValueError so a
  bad env value falls back to 300s instead of crashing at import.
- SSE streaming response is now closed via context manager (with response:)
  to guarantee connection pool return even on early break.
- Replace asyncio.get_event_loop() (deprecated) with asyncio.get_running_loop()
  in both chat and agent_chat handlers.
- create_session now calls resolve_kb_id() so KB names are accepted in addition
  to UUIDs (consistent with chat / hybrid_search).
- knowledge_base_ids description changed from REQUIRED to Strongly recommended
  to match actual schema optionality.
- run_sse() handle_sse rewritten as raw ASGI callable (scope, receive, send) to
  avoid accessing Starlette private _send attribute.
- Fix main.py comment: http transport is Streamable HTTP (MCP spec), not long-polling.
2026-05-29 16:40:29 +08:00
mileslai 8ffd1ee2d6 fix(mcp-server): restore all create_session parameters (kb_id, max_rounds, enable_rewrite, fallback_response, summary_model_id)
Restore parameters that were inadvertently removed during refactoring.
- kb_id: Required knowledge base ID (architectural shift from KB-agnostic back to KB-bound sessions)
- max_rounds, enable_rewrite, fallback_response: Session strategy configuration
- summary_model_id: Model for response summarization
- title, description: Optional session metadata

These parameters enable AI agents to fully configure session behavior.
2026-05-29 16:40:29 +08:00
mileslai e9a242c25f feat(mcp-server): add multi-transport support (stdio / SSE / HTTP) 2026-05-29 16:40:29 +08:00
yaol 00af694c52 feat(mcp): expose read-only wiki tools via Python MCP server
Add 3 read-only wiki tools (wiki_search, wiki_read_page,
wiki_index_view) to the Python MCP server, enabling external agents
like Claude Code and Codex to query WeKnora's LLM-generated wiki
pages following the LLM Wiki pattern.

Closes #1501

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-29 16:37:12 +08:00
begoniezhao f5963276d6 Refactor code for improved readability and consistency 2025-12-01 18:15:39 +08:00
begoniezhao 3e31fdeefd style: add necessary comments to improve code quality
- Add docstrings and inline comments for key functions and complex logic
- Unify comment style, eliminate magic numbers and ambiguous variable names
- No functional changes, only improve maintainability
2025-12-01 17:43:26 +08:00
begoniezhao 3a2c86df5b docs: 更新多语言文档,新增知识图谱与MCP配置指南及目录结构 2025-11-19 16:56:49 +08:00
suroy 8a40377a4a fix python dependency version for mcp 2025-10-30 18:08:47 +08:00
qzero ca704fa054 feat(MCP): MCP服务端添加使用文件创建知识的功能 2025-10-20 11:03:55 +08:00
言言学姐 9dda60bbec feat: 添加了配套mcp服务器包 2025-09-08 19:43:45 +08:00