56
/ 100
29 days ago
mcp_so

πŸ” πŸ€– 🌐 Ollama Chat with MCP

This app demonstrates use of MCP server and client in a local model chat via Ollama that incorporates web search via Serper.

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.

Install from

M8ven verifies MCPs across every public registry β€” install directly from whichever one you prefer.

// key findings
βœ…
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
βœ…
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
πŸ”
You'll be asked for 8 credentials: HUBSPOT_CLIENT_SECRET, FLASK_SECRET_KEY, SETTINGS_ENCRYPTION_KEY, CANVA_API_TOKEN, FIGMA_ACCESS_TOKEN, DB_PASSWORD, POE_API_KEY, SERPER_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// required environment variables
This server reads these from process.env. You'll be asked to provide them before it can run.
configHUBSPOT_CLIENT_IDβ€” your_hubspot_client_id
πŸ” secretHUBSPOT_CLIENT_SECRETβ€” your_hubspot_client_secret
configHUBSPOT_REDIRECT_URI
πŸ” secretFLASK_SECRET_KEY
configFRONTEND_URL
configMONGODB_URIβ€” mongodb://localhost:27017/
configMONGODB_DATABASE_NAMEβ€” mcp_chat_db
configMONGODB_COLLECTION_NAME
configDEFAULT_MODEL
configDEFAULT_OLLAMA_MODELβ€” You can select the model in the UI, or configure a default via in the backend .env file.
configREPEAT_PENALTY
configOLLAMA_REPEAT_PENALTY
configOLLAMA_API_BASE
configMONGODB_TASKS_COLLECTION_NAME
configENABLE_TASKS
configTASK_MAX_SECONDS_DEFAULT
configTASK_MAX_TOOL_CALLS_DEFAULT
configTASK_STEP_TIMEOUT_DEFAULT
configTASK_DISPATCH_INTERVAL_MS
configCODEX_DEBUGβ€” CODEX_MAX_OUTPUT_FILES=500, CODEX_MAX_OUTPUT_TOTAL_BYTES=20971520, =false
configDISABLED_MCP_SERVICESβ€” The backend starts the Canva service automatically alongside all other MCP services β€” no separate process needed. To disable it without removing the token, set =canva_service in .env.
configARTIFACTS_ROOT
configCLI_ENABLED
configENABLE_PROMPT_IMPROVER
configIMPROVER_RATE_LIMIT_PER_MIN
πŸ” secretSETTINGS_ENCRYPTION_KEYβ€” Paste the key into .env as =...
πŸ” secretCANVA_API_TOKENβ€” your_canva_personal_access_token_here
configCLI_MAX_OUTPUT_CHARS
configCLI_MAX_LOG_READ_BYTES
configCLI_ALLOWED_SERVICES
configCODEX_BINβ€” Codex Workspace: Codex CLI available on PATH (or set ), OpenAI API key configured
configCODEX_WORKSPACES_DIRβ€” CODEX_BIN=codex, =./.codex_workspaces, CODEX_MAX_CONCURRENCY=1, CODEX_RUN_TTL_HOURS=48
configCODEX_MAX_CONCURRENCYβ€” CODEX_BIN=codex, CODEX_WORKSPACES_DIR=./.codex_workspaces, =1, CODEX_RUN_TTL_HOURS=48
configCODEX_RUN_TTL_HOURSβ€” CODEX_BIN=codex, CODEX_WORKSPACES_DIR=./.codex_workspaces, CODEX_MAX_CONCURRENCY=1, =48
configCODEX_MAX_PROMPT_CHARSβ€” 20000, CODEX_MAX_STDOUT_CHARS=200000, CODEX_MAX_STDERR_CHARS=50000
configCODEX_MAX_STDOUT_CHARSβ€” CODEX_MAX_PROMPT_CHARS=20000, =200000, CODEX_MAX_STDERR_CHARS=50000
configCODEX_MAX_STDERR_CHARSβ€” CODEX_MAX_PROMPT_CHARS=20000, CODEX_MAX_STDOUT_CHARS=200000, =50000
configCODEX_MAX_FILES_IN_MANIFEST
configCODEX_MAX_FILE_BYTES_READ
configCODEX_MAX_OUTPUT_FILESβ€” 500, CODEX_MAX_OUTPUT_TOTAL_BYTES=20971520, CODEX_DEBUG=false
configCODEX_MAX_OUTPUT_TOTAL_BYTESβ€” CODEX_MAX_OUTPUT_FILES=500, =20971520, CODEX_DEBUG=false
πŸ” secretFIGMA_ACCESS_TOKENβ€” your_figma_personal_access_token_here
configDB_HOST
configDB_USERβ€” your_db_user
πŸ” secretDB_PASSWORDβ€” your_db_password
configDB_NAMEβ€” your_db_name
πŸ” secretPOE_API_KEYβ€” your_poe_api_key_here
πŸ” secretSERPER_API_KEYβ€” your_serper_api_key_here
configSMART_EXTRACT_MAX_URLSβ€” 3 # Maximum URLs to extract (default: 3)
configSMART_EXTRACT_MAX_CHARS_PER_URLβ€” 2000 # Character limit per webpage (default: 2000)
configSMART_EXTRACT_MAX_TOTAL_CHARSβ€” 5000 # Total character limit (default: 5000)
configSMART_EXTRACT_REQUEST_DELAYβ€” 1.0 # Delay between requests (default: 1.0s)
configYTA_LOG_LEVEL
configYTA_PROXYβ€” =https://user:pass@host:port
configOLLAMA_HOST
configOPENROUTER_HTTP_REFERER
configOPENROUTER_APP_NAME
configCANVA_BASE_URL
configCANVA_EXPORT_POLL_INTERVAL
configCANVA_EXPORT_TIMEOUT
configFIGMA_BASE_URL
configFIGMA_RATE_LIMIT_REQUESTSβ€” 5000 # requests per window (default: 1000)
configFIGMA_RATE_LIMIT_WINDOWβ€” 3600 # window in seconds (default: 3600)
configPOE_BASE_URL
configPOE_MAX_DOWNLOAD_BYTES
configPOE_ALLOWED_MEDIA_HOSTS
// full audit trail
The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.
// improvement guidance β€” verified publishers only
We have 7 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/redbuilding-ollama-chat-with-mcp-1lgvvl)](https://m8ven.ai/mcp/redbuilding-ollama-chat-with-mcp-1lgvvl)
commit: e200b931099e3bdcff2e91e70cdd392b2fbbe05e
code hash: ef745afa8d22cb6bc5ffc4056c3c8b15f804735e26a3d5aa6d1f93eb0e7561fa
verified: 7/2/2026, 9:18:46 AM
view raw JSON β†’