Skip to content
MCP server

MCP Context Server

An MCP server that provides persistent multimodal context storage for LLM agents.

Install
Pricing
Open source
Runs
Locally or Remotely
Version
2.2.2
Listing updated
5 days ago

About MCP Context Server

MCP Context Server is an open-source MCP server. It can run locally on your machine or as a hosted remote server.

Install

Run in a terminal

claude mcp add mcp-context-server --env POSTGRESQL_CONNECTION_STRING='<POSTGRESQL_CONNECTION_STRING>' --env POSTGRESQL_PASSWORD='<POSTGRESQL_PASSWORD>' --env ANTHROPIC_API_KEY='<ANTHROPIC_API_KEY>' --env OPENAI_API_KEY='<OPENAI_API_KEY>' --env AZURE_OPENAI_API_KEY='<AZURE_OPENAI_API_KEY>' --env HUGGINGFACEHUB_API_TOKEN='<HUGGINGFACEHUB_API_TOKEN>' --env VOYAGE_API_KEY='<VOYAGE_API_KEY>' --env LANGSMITH_API_KEY='<LANGSMITH_API_KEY>' --env MCP_AUTH_TOKEN='<MCP_AUTH_TOKEN>' -- uvx mcp-context-server

Add to claude_desktop_config.json

{
  "mcpServers": {
    "mcp-context-server": {
      "command": "uvx",
      "args": [
        "mcp-context-server"
      ],
      "env": {
        "POSTGRESQL_CONNECTION_STRING": "<POSTGRESQL_CONNECTION_STRING>",
        "POSTGRESQL_PASSWORD": "<POSTGRESQL_PASSWORD>",
        "ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>",
        "OPENAI_API_KEY": "<OPENAI_API_KEY>",
        "AZURE_OPENAI_API_KEY": "<AZURE_OPENAI_API_KEY>",
        "HUGGINGFACEHUB_API_TOKEN": "<HUGGINGFACEHUB_API_TOKEN>",
        "VOYAGE_API_KEY": "<VOYAGE_API_KEY>",
        "LANGSMITH_API_KEY": "<LANGSMITH_API_KEY>",
        "MCP_AUTH_TOKEN": "<MCP_AUTH_TOKEN>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp-context-server": {
      "command": "uvx",
      "args": [
        "mcp-context-server"
      ],
      "env": {
        "POSTGRESQL_CONNECTION_STRING": "<POSTGRESQL_CONNECTION_STRING>",
        "POSTGRESQL_PASSWORD": "<POSTGRESQL_PASSWORD>",
        "ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>",
        "OPENAI_API_KEY": "<OPENAI_API_KEY>",
        "AZURE_OPENAI_API_KEY": "<AZURE_OPENAI_API_KEY>",
        "HUGGINGFACEHUB_API_TOKEN": "<HUGGINGFACEHUB_API_TOKEN>",
        "VOYAGE_API_KEY": "<VOYAGE_API_KEY>",
        "LANGSMITH_API_KEY": "<LANGSMITH_API_KEY>",
        "MCP_AUTH_TOKEN": "<MCP_AUTH_TOKEN>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "mcp-context-server": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-context-server"
      ],
      "env": {
        "POSTGRESQL_CONNECTION_STRING": "<POSTGRESQL_CONNECTION_STRING>",
        "POSTGRESQL_PASSWORD": "<POSTGRESQL_PASSWORD>",
        "ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>",
        "OPENAI_API_KEY": "<OPENAI_API_KEY>",
        "AZURE_OPENAI_API_KEY": "<AZURE_OPENAI_API_KEY>",
        "HUGGINGFACEHUB_API_TOKEN": "<HUGGINGFACEHUB_API_TOKEN>",
        "VOYAGE_API_KEY": "<VOYAGE_API_KEY>",
        "LANGSMITH_API_KEY": "<LANGSMITH_API_KEY>",
        "MCP_AUTH_TOKEN": "<MCP_AUTH_TOKEN>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-context-server": {
      "command": "uvx",
      "args": [
        "mcp-context-server"
      ],
      "env": {
        "POSTGRESQL_CONNECTION_STRING": "<POSTGRESQL_CONNECTION_STRING>",
        "POSTGRESQL_PASSWORD": "<POSTGRESQL_PASSWORD>",
        "ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>",
        "OPENAI_API_KEY": "<OPENAI_API_KEY>",
        "AZURE_OPENAI_API_KEY": "<AZURE_OPENAI_API_KEY>",
        "HUGGINGFACEHUB_API_TOKEN": "<HUGGINGFACEHUB_API_TOKEN>",
        "VOYAGE_API_KEY": "<VOYAGE_API_KEY>",
        "LANGSMITH_API_KEY": "<LANGSMITH_API_KEY>",
        "MCP_AUTH_TOKEN": "<MCP_AUTH_TOKEN>"
      }
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "mcp-context-server": {
      "command": "uvx",
      "args": [
        "mcp-context-server"
      ],
      "env": {
        "POSTGRESQL_CONNECTION_STRING": "<POSTGRESQL_CONNECTION_STRING>",
        "POSTGRESQL_PASSWORD": "<POSTGRESQL_PASSWORD>",
        "ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>",
        "OPENAI_API_KEY": "<OPENAI_API_KEY>",
        "AZURE_OPENAI_API_KEY": "<AZURE_OPENAI_API_KEY>",
        "HUGGINGFACEHUB_API_TOKEN": "<HUGGINGFACEHUB_API_TOKEN>",
        "VOYAGE_API_KEY": "<VOYAGE_API_KEY>",
        "LANGSMITH_API_KEY": "<LANGSMITH_API_KEY>",
        "MCP_AUTH_TOKEN": "<MCP_AUTH_TOKEN>"
      }
    }
  }
}

Configuration

  • LOG_LEVELLog level
  • STORAGE_BACKENDStorage backend type: sqlite (default) or postgresql
  • MAX_IMAGE_SIZE_MBMaximum individual image size in megabytes
  • MAX_TOTAL_SIZE_MBMaximum total request size in megabytes
  • DB_PATHCustom database file location path
  • POOL_MAX_READERSMaximum number of concurrent read connections in the pool
  • POOL_MAX_WRITERSMaximum number of concurrent write connections in the pool
  • POOL_CONNECTION_TIMEOUT_SConnection timeout in seconds
  • POOL_IDLE_TIMEOUT_SIdle connection timeout in seconds
  • POOL_HEALTH_CHECK_INTERVAL_SConnection health check interval in seconds
  • RETRY_MAX_RETRIESMaximum number of retry attempts for failed operations
  • RETRY_BASE_DELAY_SBase delay in seconds between retry attempts
  • RETRY_MAX_DELAY_SMaximum delay in seconds between retry attempts
  • RETRY_JITTEREnable random jitter in retry delays
  • RETRY_BACKOFF_FACTORExponential backoff multiplication factor for retries
  • SQLITE_FOREIGN_KEYSEnable SQLite foreign key constraints
  • SQLITE_JOURNAL_MODESQLite journal mode (e.g., WAL, DELETE)
  • SQLITE_SYNCHRONOUSSQLite synchronous mode (e.g., NORMAL, FULL, OFF)
  • SQLITE_TEMP_STORESQLite temporary storage location (e.g., MEMORY, FILE)
  • SQLITE_MMAP_SIZESQLite memory-mapped I/O size in bytes
  • SQLITE_CACHE_SIZESQLite cache size (negative value for KB, positive for pages)
  • SQLITE_PAGE_SIZESQLite page size in bytes
  • SQLITE_WAL_AUTOCHECKPOINTSQLite WAL autocheckpoint threshold in pages
  • SQLITE_BUSY_TIMEOUT_MSSQLite busy timeout in milliseconds
  • SQLITE_WAL_CHECKPOINTSQLite WAL checkpoint mode (e.g., PASSIVE, FULL, RESTART)
  • SHUTDOWN_TIMEOUT_SServer shutdown timeout in seconds
  • SHUTDOWN_TIMEOUT_TEST_STest mode shutdown timeout in seconds
  • QUEUE_TIMEOUT_SQueue operation timeout in seconds
  • QUEUE_TIMEOUT_TEST_STest mode queue timeout in seconds
  • CIRCUIT_BREAKER_FAILURE_THRESHOLDCircuit breaker failure threshold before opening
  • CIRCUIT_BREAKER_RECOVERY_TIMEOUT_SCircuit breaker recovery timeout in seconds
  • CIRCUIT_BREAKER_HALF_OPEN_MAX_CALLSMaximum calls allowed in circuit breaker half-open state
  • POSTGRESQL_CONNECTION_STRINGComplete PostgreSQL connection string (overrides individual settings if provided)
  • POSTGRESQL_HOSTPostgreSQL server host address
  • POSTGRESQL_PORTPostgreSQL server port number
  • POSTGRESQL_USERPostgreSQL database username
  • POSTGRESQL_PASSWORDPostgreSQL database password
  • POSTGRESQL_DATABASEPostgreSQL database name
  • POSTGRESQL_POOL_MINPostgreSQL connection pool minimum size
  • POSTGRESQL_POOL_MAXPostgreSQL connection pool maximum size
  • POSTGRESQL_POOL_TIMEOUT_SPostgreSQL connection pool timeout in seconds
  • POSTGRESQL_COMMAND_TIMEOUT_SPostgreSQL command execution timeout in seconds
  • POSTGRESQL_MIGRATION_TIMEOUT_STimeout in seconds for PostgreSQL migration operations (default: 300)
  • POSTGRESQL_MAX_INACTIVE_LIFETIME_SClose idle PostgreSQL connections after this many seconds (0 to disable, default: 300)
  • POSTGRESQL_MAX_QUERIESRecycle PostgreSQL connections after this many queries (0 to disable, default: 10000)
  • POSTGRESQL_TCP_KEEPALIVES_IDLE_SSeconds of idle time before sending first TCP keepalive probe (0 to disable, default: 15)
  • POSTGRESQL_TCP_KEEPALIVES_INTERVAL_SSeconds between subsequent TCP keepalive probes (0 to disable, default: 5)
  • POSTGRESQL_TCP_KEEPALIVES_COUNTNumber of failed TCP keepalive probes before connection is considered dead (0 to disable, default: 3)
  • POSTGRESQL_STATEMENT_CACHE_SIZEasyncpg prepared statement cache size. Set to 0 for external pooler compatibility (PgBouncer transaction mode, Pgpool-II, etc.). Default: 100
  • POSTGRESQL_MAX_CACHED_STATEMENT_LIFETIME_SMaximum lifetime of cached prepared statements in seconds (default: 300). Has no effect when statement_cache_size=0
  • POSTGRESQL_MAX_CACHEABLE_STATEMENT_SIZEMaximum size of statement to cache in bytes (default: 15360). Has no effect when statement_cache_size=0
  • POSTGRESQL_SSL_MODEPostgreSQL SSL mode (disable, allow, prefer, require, verify-ca, verify-full)
  • POSTGRESQL_SCHEMAPostgreSQL schema name for table and index operations (default: public)
  • ENABLE_SEMANTIC_SEARCHEnable semantic search functionality
  • ENABLE_EMBEDDING_GENERATIONEnable embedding generation for stored context. Default true - server fails if dependencies not met. Set false to disable embeddings.
  • OLLAMA_HOSTOllama API host URL for embedding generation
  • OLLAMA_AUTO_PULLAutomatically pull missing Ollama models on startup (default: true)
  • OLLAMA_PULL_TIMEOUT_STimeout in seconds for pulling Ollama models (default: 900, range: 30-3600)
  • EMBEDDING_OLLAMA_TRUNCATEOllama embedding truncation mode: false (default) returns error when context exceeded, true enables silent truncation
  • EMBEDDING_OLLAMA_NUM_CTXOllama embedding context window size in tokens (default: 4096, range: 512-2097152)
  • EMBEDDING_MODELEmbedding model name for semantic search
  • EMBEDDING_DIMEmbedding vector dimensions
  • EMBEDDING_TIMEOUT_STimeout in seconds for embedding generation API calls
  • EMBEDDING_RETRY_MAX_ATTEMPTSMaximum number of retry attempts for embedding generation
  • EMBEDDING_RETRY_BASE_DELAY_SBase delay in seconds between retry attempts (with exponential backoff)
  • EMBEDDING_MAX_CONCURRENTMaximum concurrent embedding generation operations (default: 3, range: 1-20)
  • ENABLE_SUMMARY_GENERATIONEnable summary generation for stored context. Default true - server fails if dependencies not met. Set false to disable summaries.
  • SUMMARY_PROVIDERSummary provider: ollama (default), openai, or anthropic
  • SUMMARY_MODELSummary generation model name (default: qwen3:0.6b)
  • SUMMARY_MAX_TOKENSMaximum output tokens for summary generation (default: 4000, range: 50-16384). Increase if summaries are truncated by reasoning models
  • SUMMARY_TIMEOUT_STimeout in seconds for summary generation API calls
  • SUMMARY_RETRY_MAX_ATTEMPTSMaximum number of retry attempts for summary generation
  • SUMMARY_RETRY_BASE_DELAY_SBase delay in seconds between retry attempts (with exponential backoff)
  • SUMMARY_MAX_CONCURRENTMaximum concurrent summary generation operations (default: 3, range: 1-20)
  • SUMMARY_PROMPTCustom summarization prompt. Overrides the built-in default. Used as system message for the LLM.
  • SUMMARY_MIN_CONTENT_LENGTHMinimum text content length in characters to trigger summary generation (default: 500, range: 0-10000). Set to 0 to always generate.
  • SUMMARY_OLLAMA_NUM_CTXOllama summary context window size in tokens (default: 32768, range: 512-2097152)
  • SUMMARY_OLLAMA_TRUNCATEOllama summary truncation mode: false (default) returns error when context exceeded, true enables silent truncation
  • SUMMARY_OPENAI_REASONING_EFFORTReasoning effort level for OpenAI reasoning models (default: low). Valid values vary by generation: gpt-5: low, medium, high; gpt-5.1+: none, low, medium, high, xhigh. Default low is universally valid across all generations
  • SUMMARY_ANTHROPIC_EFFORTEffort level for Anthropic Claude models (default: none). Valid values: max, high, medium, low. Controls inference effort (adaptive thinking)
  • ANTHROPIC_API_KEYAnthropic API key for summary generation
  • ENABLE_FTSEnable full-text search functionality
  • FTS_LANGUAGELanguage for FTS stemming (e.g., english, german, french)
  • FTS_RERANK_WINDOW_SIZECharacters of context around each FTS match for reranking passage extraction (default: 750)
  • FTS_RERANK_GAP_MERGEMerge FTS match regions within this character distance (default: 100)
  • ENABLE_HYBRID_SEARCHEnable hybrid search combining FTS and semantic search with RRF fusion
  • HYBRID_RRF_KRRF smoothing constant for hybrid search (default 60)
  • HYBRID_RRF_OVERFETCHMultiplier for over-fetching results before RRF fusion (default: 2)
  • HYBRID_FTS_OR_THRESHOLDMinimum significant query terms to switch hybrid FTS from AND to OR logic (default: 4)
  • SEARCH_DEFAULT_SORT_BYDefault sort order for search results: relevance (only 'relevance' supported in current version)
  • SEARCH_TRUNCATION_LENGTHMaximum character length for truncated text_content in search results (default: 300, range: 50-1000)
  • ENABLE_CHUNKINGEnable text chunking for embedding generation (default: true)
  • CHUNK_SIZETarget chunk size in characters (default: 1500)
  • CHUNK_OVERLAPOverlap between chunks in characters (default: 150)
  • CHUNK_AGGREGATIONChunk score aggregation method: max (only 'max' supported in current version)
  • CHUNK_DEDUP_OVERFETCHMultiplier for over-fetching chunks before deduplication (default: 5)
  • ENABLE_RERANKINGEnable cross-encoder reranking of search results (default: true)
  • RERANKING_PROVIDERReranking provider (default: flashrank)
  • RERANKING_MODELReranking model name (default: ms-marco-MiniLM-L-12-v2)
  • RERANKING_MAX_LENGTHMaximum input length for reranking in tokens (default: 512)
  • RERANKING_OVERFETCHMultiplier for over-fetching results before reranking (default: 4)
  • RERANKING_CACHE_DIRDirectory for caching reranking models
  • RERANKING_CHARS_PER_TOKENEstimated characters per token for passage size validation (default: 4.0, range: 2.0-8.0)
  • RERANKING_INTRA_OP_THREADSONNX Runtime intra-operation parallelism threads for reranking (default: 0 = auto-detect)
  • RERANKING_CPU_MEM_ARENAEnable ONNX Runtime CPU memory arena for reranking (default: false)
  • RERANKING_BATCH_SIZEMaximum passages per ONNX Runtime inference batch during reranking (default: 32)
  • EMBEDDING_PROVIDEREmbedding provider: ollama (default), openai, azure, huggingface, or voyage
  • OPENAI_API_KEYOpenAI API key for OpenAI embedding provider
  • OPENAI_API_BASECustom base URL for OpenAI-compatible APIs
  • OPENAI_ORGANIZATIONOpenAI organization ID
  • AZURE_OPENAI_API_KEYAzure OpenAI API key
  • AZURE_OPENAI_ENDPOINTAzure OpenAI endpoint URL
  • AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAMEAzure OpenAI embedding deployment name
  • AZURE_OPENAI_API_VERSIONAzure OpenAI API version (default: 2024-02-01)
  • HUGGINGFACEHUB_API_TOKENHuggingFace Hub API token for HuggingFace embedding provider
  • VOYAGE_API_KEYVoyage AI API key for Voyage embedding provider
  • VOYAGE_TRUNCATIONVoyage AI truncation mode: false (default) returns error when context exceeded, true enables silent truncation
  • VOYAGE_BATCH_SIZEVoyage AI batch size for embedding requests
  • LANGSMITH_TRACINGEnable LangSmith tracing
  • LANGSMITH_API_KEYLangSmith API key
  • LANGSMITH_PROJECTLangSmith project name
  • LANGSMITH_ENDPOINTLangSmith API endpoint URL
  • METADATA_INDEXED_FIELDSComma-separated list of metadata fields to index (field:type format)
  • METADATA_INDEX_SYNC_MODEIndex sync mode: strict (fail), auto (sync), warn (log), additive (default, add missing only)
  • MCP_TRANSPORTTransport mode: stdio for local, http for Docker/remote
  • FASTMCP_HOSTHTTP bind address (use 0.0.0.0 for Docker)
  • FASTMCP_PORTHTTP port number
  • FASTMCP_STATELESS_HTTPEnable stateless HTTP mode for horizontal scaling. Enabled by default as the server has no stateful MCP features. Set to false only if you need server-side MCP session tracking.
  • DISABLED_TOOLSComma-separated list of tools to disable (e.g., delete_context,update_context)
  • MCP_AUTH_TOKENBearer token for HTTP authentication (required when using SimpleTokenVerifier)
  • MCP_AUTH_CLIENT_IDClient ID to assign to authenticated requests
  • MCP_AUTH_PROVIDERAuthentication provider: none (default), simple_token
  • MCP_SERVER_INSTRUCTIONSCustom server instructions text. Overrides built-in default. Set to empty string to disable.
  • LOG_LEVELLog level
  • STORAGE_BACKENDStorage backend type: sqlite (default) or postgresql
  • MAX_IMAGE_SIZE_MBMaximum individual image size in megabytes
  • MAX_TOTAL_SIZE_MBMaximum total request size in megabytes
  • DB_PATHCustom database file location path
  • POOL_MAX_READERSMaximum number of concurrent read connections in the pool
  • POOL_MAX_WRITERSMaximum number of concurrent write connections in the pool
  • POOL_CONNECTION_TIMEOUT_SConnection timeout in seconds
  • POOL_IDLE_TIMEOUT_SIdle connection timeout in seconds
  • POOL_HEALTH_CHECK_INTERVAL_SConnection health check interval in seconds
  • RETRY_MAX_RETRIESMaximum number of retry attempts for failed operations
  • RETRY_BASE_DELAY_SBase delay in seconds between retry attempts
  • RETRY_MAX_DELAY_SMaximum delay in seconds between retry attempts
  • RETRY_JITTEREnable random jitter in retry delays
  • RETRY_BACKOFF_FACTORExponential backoff multiplication factor for retries
  • SQLITE_FOREIGN_KEYSEnable SQLite foreign key constraints
  • SQLITE_JOURNAL_MODESQLite journal mode (e.g., WAL, DELETE)
  • SQLITE_SYNCHRONOUSSQLite synchronous mode (e.g., NORMAL, FULL, OFF)
  • SQLITE_TEMP_STORESQLite temporary storage location (e.g., MEMORY, FILE)
  • SQLITE_MMAP_SIZESQLite memory-mapped I/O size in bytes
  • SQLITE_CACHE_SIZESQLite cache size (negative value for KB, positive for pages)
  • SQLITE_PAGE_SIZESQLite page size in bytes
  • SQLITE_WAL_AUTOCHECKPOINTSQLite WAL autocheckpoint threshold in pages
  • SQLITE_BUSY_TIMEOUT_MSSQLite busy timeout in milliseconds
  • SQLITE_WAL_CHECKPOINTSQLite WAL checkpoint mode (e.g., PASSIVE, FULL, RESTART)
  • SHUTDOWN_TIMEOUT_SServer shutdown timeout in seconds
  • SHUTDOWN_TIMEOUT_TEST_STest mode shutdown timeout in seconds
  • QUEUE_TIMEOUT_SQueue operation timeout in seconds
  • QUEUE_TIMEOUT_TEST_STest mode queue timeout in seconds
  • CIRCUIT_BREAKER_FAILURE_THRESHOLDCircuit breaker failure threshold before opening
  • CIRCUIT_BREAKER_RECOVERY_TIMEOUT_SCircuit breaker recovery timeout in seconds
  • CIRCUIT_BREAKER_HALF_OPEN_MAX_CALLSMaximum calls allowed in circuit breaker half-open state
  • POSTGRESQL_CONNECTION_STRINGComplete PostgreSQL connection string (overrides individual settings if provided)
  • POSTGRESQL_HOSTPostgreSQL server host address
  • POSTGRESQL_PORTPostgreSQL server port number
  • POSTGRESQL_USERPostgreSQL database username
  • POSTGRESQL_PASSWORDPostgreSQL database password
  • POSTGRESQL_DATABASEPostgreSQL database name
  • POSTGRESQL_POOL_MINPostgreSQL connection pool minimum size
  • POSTGRESQL_POOL_MAXPostgreSQL connection pool maximum size
  • POSTGRESQL_POOL_TIMEOUT_SPostgreSQL connection pool timeout in seconds
  • POSTGRESQL_COMMAND_TIMEOUT_SPostgreSQL command execution timeout in seconds
  • POSTGRESQL_MIGRATION_TIMEOUT_STimeout in seconds for PostgreSQL migration operations (default: 300)
  • POSTGRESQL_MAX_INACTIVE_LIFETIME_SClose idle PostgreSQL connections after this many seconds (0 to disable, default: 300)
  • POSTGRESQL_MAX_QUERIESRecycle PostgreSQL connections after this many queries (0 to disable, default: 10000)
  • POSTGRESQL_TCP_KEEPALIVES_IDLE_SSeconds of idle time before sending first TCP keepalive probe (0 to disable, default: 15)
  • POSTGRESQL_TCP_KEEPALIVES_INTERVAL_SSeconds between subsequent TCP keepalive probes (0 to disable, default: 5)
  • POSTGRESQL_TCP_KEEPALIVES_COUNTNumber of failed TCP keepalive probes before connection is considered dead (0 to disable, default: 3)
  • POSTGRESQL_STATEMENT_CACHE_SIZEasyncpg prepared statement cache size. Set to 0 for external pooler compatibility (PgBouncer transaction mode, Pgpool-II, etc.). Default: 100
  • POSTGRESQL_MAX_CACHED_STATEMENT_LIFETIME_SMaximum lifetime of cached prepared statements in seconds (default: 300). Has no effect when statement_cache_size=0
  • POSTGRESQL_MAX_CACHEABLE_STATEMENT_SIZEMaximum size of statement to cache in bytes (default: 15360). Has no effect when statement_cache_size=0
  • POSTGRESQL_SSL_MODEPostgreSQL SSL mode (disable, allow, prefer, require, verify-ca, verify-full)
  • POSTGRESQL_SCHEMAPostgreSQL schema name for table and index operations (default: public)
  • ENABLE_SEMANTIC_SEARCHEnable semantic search functionality
  • ENABLE_EMBEDDING_GENERATIONEnable embedding generation for stored context. Default true - server fails if dependencies not met. Set false to disable embeddings.
  • OLLAMA_HOSTOllama API host URL for embedding generation
  • OLLAMA_AUTO_PULLAutomatically pull missing Ollama models on startup (default: true)
  • OLLAMA_PULL_TIMEOUT_STimeout in seconds for pulling Ollama models (default: 900, range: 30-3600)
  • EMBEDDING_OLLAMA_TRUNCATEOllama embedding truncation mode: false (default) returns error when context exceeded, true enables silent truncation
  • EMBEDDING_OLLAMA_NUM_CTXOllama embedding context window size in tokens (default: 4096, range: 512-2097152)
  • EMBEDDING_MODELEmbedding model name for semantic search
  • EMBEDDING_DIMEmbedding vector dimensions
  • EMBEDDING_TIMEOUT_STimeout in seconds for embedding generation API calls
  • EMBEDDING_RETRY_MAX_ATTEMPTSMaximum number of retry attempts for embedding generation
  • EMBEDDING_RETRY_BASE_DELAY_SBase delay in seconds between retry attempts (with exponential backoff)
  • EMBEDDING_MAX_CONCURRENTMaximum concurrent embedding generation operations (default: 3, range: 1-20)
  • ENABLE_SUMMARY_GENERATIONEnable summary generation for stored context. Default true - server fails if dependencies not met. Set false to disable summaries.
  • SUMMARY_PROVIDERSummary provider: ollama (default), openai, or anthropic
  • SUMMARY_MODELSummary generation model name (default: qwen3:0.6b)
  • SUMMARY_MAX_TOKENSMaximum output tokens for summary generation (default: 4000, range: 50-16384). Increase if summaries are truncated by reasoning models
  • SUMMARY_TIMEOUT_STimeout in seconds for summary generation API calls
  • SUMMARY_RETRY_MAX_ATTEMPTSMaximum number of retry attempts for summary generation
  • SUMMARY_RETRY_BASE_DELAY_SBase delay in seconds between retry attempts (with exponential backoff)
  • SUMMARY_MAX_CONCURRENTMaximum concurrent summary generation operations (default: 3, range: 1-20)
  • SUMMARY_PROMPTCustom summarization prompt. Overrides the built-in default. Used as system message for the LLM.
  • SUMMARY_MIN_CONTENT_LENGTHMinimum text content length in characters to trigger summary generation (default: 500, range: 0-10000). Set to 0 to always generate.
  • SUMMARY_OLLAMA_NUM_CTXOllama summary context window size in tokens (default: 32768, range: 512-2097152)
  • SUMMARY_OLLAMA_TRUNCATEOllama summary truncation mode: false (default) returns error when context exceeded, true enables silent truncation
  • SUMMARY_OPENAI_REASONING_EFFORTReasoning effort level for OpenAI reasoning models (default: low). Valid values vary by generation: gpt-5: low, medium, high; gpt-5.1+: none, low, medium, high, xhigh. Default low is universally valid across all generations
  • SUMMARY_ANTHROPIC_EFFORTEffort level for Anthropic Claude models (default: none). Valid values: max, high, medium, low. Controls inference effort (adaptive thinking)
  • ANTHROPIC_API_KEYAnthropic API key for summary generation
  • ENABLE_FTSEnable full-text search functionality
  • FTS_LANGUAGELanguage for FTS stemming (e.g., english, german, french)
  • FTS_RERANK_WINDOW_SIZECharacters of context around each FTS match for reranking passage extraction (default: 750)
  • FTS_RERANK_GAP_MERGEMerge FTS match regions within this character distance (default: 100)
  • ENABLE_HYBRID_SEARCHEnable hybrid search combining FTS and semantic search with RRF fusion
  • HYBRID_RRF_KRRF smoothing constant for hybrid search (default 60)
  • HYBRID_RRF_OVERFETCHMultiplier for over-fetching results before RRF fusion (default: 2)
  • HYBRID_FTS_OR_THRESHOLDMinimum significant query terms to switch hybrid FTS from AND to OR logic (default: 4)
  • SEARCH_DEFAULT_SORT_BYDefault sort order for search results: relevance (only 'relevance' supported in current version)
  • SEARCH_TRUNCATION_LENGTHMaximum character length for truncated text_content in search results (default: 300, range: 50-1000)
  • ENABLE_CHUNKINGEnable text chunking for embedding generation (default: true)
  • CHUNK_SIZETarget chunk size in characters (default: 1500)
  • CHUNK_OVERLAPOverlap between chunks in characters (default: 150)
  • CHUNK_AGGREGATIONChunk score aggregation method: max (only 'max' supported in current version)
  • CHUNK_DEDUP_OVERFETCHMultiplier for over-fetching chunks before deduplication (default: 5)
  • ENABLE_RERANKINGEnable cross-encoder reranking of search results (default: true)
  • RERANKING_PROVIDERReranking provider (default: flashrank)
  • RERANKING_MODELReranking model name (default: ms-marco-MiniLM-L-12-v2)
  • RERANKING_MAX_LENGTHMaximum input length for reranking in tokens (default: 512)
  • RERANKING_OVERFETCHMultiplier for over-fetching results before reranking (default: 4)
  • RERANKING_CACHE_DIRDirectory for caching reranking models
  • RERANKING_CHARS_PER_TOKENEstimated characters per token for passage size validation (default: 4.0, range: 2.0-8.0)
  • RERANKING_INTRA_OP_THREADSONNX Runtime intra-operation parallelism threads for reranking (default: 0 = auto-detect)
  • RERANKING_CPU_MEM_ARENAEnable ONNX Runtime CPU memory arena for reranking (default: false)
  • RERANKING_BATCH_SIZEMaximum passages per ONNX Runtime inference batch during reranking (default: 32)
  • EMBEDDING_PROVIDEREmbedding provider: ollama (default), openai, azure, huggingface, or voyage
  • OPENAI_API_KEYOpenAI API key for OpenAI embedding provider
  • OPENAI_API_BASECustom base URL for OpenAI-compatible APIs
  • OPENAI_ORGANIZATIONOpenAI organization ID
  • AZURE_OPENAI_API_KEYAzure OpenAI API key
  • AZURE_OPENAI_ENDPOINTAzure OpenAI endpoint URL
  • AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAMEAzure OpenAI embedding deployment name
  • AZURE_OPENAI_API_VERSIONAzure OpenAI API version (default: 2024-02-01)
  • HUGGINGFACEHUB_API_TOKENHuggingFace Hub API token for HuggingFace embedding provider
  • VOYAGE_API_KEYVoyage AI API key for Voyage embedding provider
  • VOYAGE_TRUNCATIONVoyage AI truncation mode: false (default) returns error when context exceeded, true enables silent truncation
  • VOYAGE_BATCH_SIZEVoyage AI batch size for embedding requests
  • LANGSMITH_TRACINGEnable LangSmith tracing
  • LANGSMITH_API_KEYLangSmith API key
  • LANGSMITH_PROJECTLangSmith project name
  • LANGSMITH_ENDPOINTLangSmith API endpoint URL
  • METADATA_INDEXED_FIELDSComma-separated list of metadata fields to index (field:type format)
  • METADATA_INDEX_SYNC_MODEIndex sync mode: strict (fail), auto (sync), warn (log), additive (default, add missing only)
  • MCP_TRANSPORTTransport mode: stdio for local, http for Docker/remote
  • FASTMCP_HOSTHTTP bind address (use 0.0.0.0 for Docker)
  • FASTMCP_PORTHTTP port number
  • FASTMCP_STATELESS_HTTPEnable stateless HTTP mode for horizontal scaling. Enabled by default as the server has no stateful MCP features. Set to false only if you need server-side MCP session tracking.
  • DISABLED_TOOLSComma-separated list of tools to disable (e.g., delete_context,update_context)
  • MCP_AUTH_TOKENBearer token for HTTP authentication (required when using SimpleTokenVerifier)
  • MCP_AUTH_CLIENT_IDClient ID to assign to authenticated requests
  • MCP_AUTH_PROVIDERAuthentication provider: none (default), simple_token
  • MCP_SERVER_INSTRUCTIONSCustom server instructions text. Overrides built-in default. Set to empty string to disable.

Pricing

Open source

MCP Context Server FAQ

Is MCP Context Server free?

Yes. MCP Context Server is open source, so you can use and self-host it for free.

How do I add MCP Context Server to Claude Code?

Run this command in your terminal: claude mcp add mcp-context-server --env POSTGRESQL_CONNECTION_STRING='<POSTGRESQL_CONNECTION_STRING>' --env POSTGRESQL_PASSWORD='<POSTGRESQL_PASSWORD>' --env ANTHROPIC_API_KEY='<ANTHROPIC_API_KEY>' --env OPENAI_API_KEY='<OPENAI_API_KEY>' --env AZURE_OPENAI_API_KEY='<AZURE_OPENAI_API_KEY>' --env HUGGINGFACEHUB_API_TOKEN='<HUGGINGFACEHUB_API_TOKEN>' --env VOYAGE_API_KEY='<VOYAGE_API_KEY>' --env LANGSMITH_API_KEY='<LANGSMITH_API_KEY>' --env MCP_AUTH_TOKEN='<MCP_AUTH_TOKEN>' -- uvx mcp-context-server