Flexible GraphRAGBLOCK
Python, LlamaIndex, LangChain, 15 Property Graph, 4 RDF , 10 Vector, OpenSearch, Elasticsearch DBs. 14 data sources, 10 auto sync: Alfresco, Nuxeo, etc. KG auto-building, Ontologies, LLMs, Docling, LlamaParse, LiteParse, GraphRAG, RAG, Hybrid Search, AI Chat. TypeScript React, Vue, Angular frontends
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://pypi.org/project/flexible-graphrag/) [](https://pepy.tech/project/flexible-graphrag) [](https://pypi.org/project/flexible-graphrag-mcp/) [](https://pepy.tech/project/flexible-graphrag-mcp) [](https://opensource.org/licenses/Apache-2.0) [](https://www.python.org/) [](https://react.dev/) [](https://angular.dev/) [](https://vuejs.org/) [](https://hub.docker.com/u/integratedsemantics) [](https://deepwiki.com/stevereiner/flexible-graphrag) [](https://stevereiner.github.io/flexible-graphrag/) [](https://integratedsemantics.org)
c3215a5ba72cOBSERVED · 2026-10-06Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add flexible-graphrag-vue --env AGE_PASSWORD=${AGE_PASSWORD} --env ALFRESCO_AUTH_METHOD=${ALFRESCO_AUTH_METHOD} --env ALFRESCO_OAUTH2_ACCESS_TOKEN=${ALFRESCO_OAUTH2_ACCESS_TOKEN} --env ALFRESCO_OAUTH2_CLIENT_ID=${ALFRESCO_OAUTH2_CLIENT_ID} -- npx -y [email protected]{
"mcpServers": {
"flexible-graphrag-vue": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"AGE_PASSWORD": "${AGE_PASSWORD}",
"ALFRESCO_AUTH_METHOD": "${ALFRESCO_AUTH_METHOD}",
"ALFRESCO_OAUTH2_ACCESS_TOKEN": "${ALFRESCO_OAUTH2_ACCESS_TOKEN}",
"ALFRESCO_OAUTH2_CLIENT_ID": "${ALFRESCO_OAUTH2_CLIENT_ID}"
}
}
}
}Exposed tools (9)
9 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
check_processing_status | read | |
get_python_info | read | Get information about the Python environment of the backend |
get_system_status | read | Get the current status of the flexible-graphrag system |
health_check | read | Check if the backend is healthy and responsive |
ingest_documents | read | |
ingest_text | read | |
query_documents | read | |
search_documents | read | |
test_with_sample | read | Test the system with sample text for quick verification |
Trust audit
BLOCKgrade F · trust 35/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (10 observation(s))
- Network
- declared (18 observation(s))
- Shell
- declared (5 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
"embedding_factory: OPENAI_VERIFY_SSL=false — creating httpx.Client(verify=False)"
return httpx.Client(verify=False)
session.verify = False
with httpx.Client(follow_redirects=False, verify=False, timeout=30) as c:
# Configure RDF Graph Databases
excel-2plus2.xlsx
word-hello-world.docx
_m = importlib.import_module(_mod_name)
importlib.import_module(mod_name)
importlib.import_module(coco_module)
mod = importlib.import_module(mod_name)
importlib.import_module(mod)
print("access_token :", token.get("access_token"))print("refresh_token:", token.get("refresh_token"))print("expires_in :", token.get("expires_in"))print("access_token :", token.get("access_token"))print("refresh_token:", token.get("refresh_token"))callback_url = loc if loc.startswith("http") else (REDIR + loc[loc.find("?"):])print("\nCALLBACK:", callback_url)token = auth.request_token(code_verifier=verifier, authorization_response=callback_url, state=state)
command: etcd -advertise-client-urls=http://127.0.0.1:2379 -listen-client-urls http://0.0.0.0:2379 --data-dir /etcd
- **`docker/docker.env`** — Added `ONTOLOGY_DIR=schemas/` override (resolves against container `/app` cwd) so `USE_ONTOLOGY=true` works in full-stack Docker without changing `.env`. Added `POSTGRES_IN
POSTGRES_INCREMENTAL_URL=postgresql://postgres:password@localhost:5433/postgres
`POSTGRES_INCREMENTAL_URL=postgresql://postgres:password@postgres-pgvector:5432/flexible_graphrag_incremental`
POSTGRES_INCREMENTAL_URL=postgresql://postgres:[email protected]:5433/flexible_graphrag_incremental
Gates applied: no_behavioural_pass.
c3215a5ba72cfull audit observations/trust-audit/mcp-server/stevereiner__flexible-graphrag.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | c3215a5ba72c | BLOCK | F | 35 | first audit |
Questions
What is the Flexible GraphRAG MCP server?
Python, LlamaIndex, LangChain, 15 Property Graph, 4 RDF , 10 Vector, OpenSearch, Elasticsearch DBs. 14 data sources, 10 auto sync: Alfresco, Nuxeo, etc. KG auto-building, Ontologies, LLMs, Docling, LlamaParse, LiteParse, GraphRAG, RAG, Hybrid Search, AI Chat. TypeScript React, Vue, Angular frontends
What tools does Flexible GraphRAG expose?
9 in total: 9 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Flexible GraphRAG safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (35/100) and found 5 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does Flexible GraphRAG need?
It reads AGE_PASSWORD, ALFRESCO_AUTH_METHOD, ALFRESCO_OAUTH2_ACCESS_TOKEN, ALFRESCO_OAUTH2_CLIENT_ID, ALFRESCO_OAUTH2_CLIENT_SECRET, ALFRESCO_OAUTH2_GRANT_TYPE, ALFRESCO_OAUTH2_REFRESH_TOKEN, ALFRESCO_OAUTH2_SCOPE, ALFRESCO_OAUTH2_TOKEN_ENDPOINT, ALFRESCO_PASSWORD, ALFRESCO_SYNC_PASSWORD and ANTHROPIC_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (c3215a5ba72c), read on 2026-10-06. The repository is watched and re-audited when it changes.