cosmic-mcp

All servers

mcp-context-server

io.github.alex-feel/mcp-context-server ยท version 2.2.2

Community listing. Not installed or verified by cosmic-mcp. Read the source and its permissions before you run it.

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

https://github.com/alex-feel/mcp-context-server

Quick facts

  • Listing: Community
  • Published Mar 28, 20:10 UTC
  • Transport: stdio
  • Package: pypi mcp-context-server 2.2.2
  • Listed by cosmic-mcp: Nov 9, 04:25 UTC
  • Repository: https://github.com/alex-feel/mcp-context-server
  • PyPI: https://pypi.org/project/mcp-context-server/
  • Needs settings: LOG_LEVEL STORAGE_BACKEND MAX_IMAGE_SIZE_MB MAX_TOTAL_SIZE_MB DB_PATH POOL_MAX_READERS POOL_MAX_WRITERS POOL_CONNECTION_TIMEOUT_S POOL_IDLE_TIMEOUT_S POOL_HEALTH_CHECK_INTERVAL_S RETRY_MAX_RETRIES RETRY_BASE_DELAY_S RETRY_MAX_DELAY_S RETRY_JITTER RETRY_BACKOFF_FACTOR SQLITE_FOREIGN_KEYS SQLITE_JOURNAL_MODE SQLITE_SYNCHRONOUS SQLITE_TEMP_STORE SQLITE_MMAP_SIZE SQLITE_CACHE_SIZE SQLITE_PAGE_SIZE SQLITE_WAL_AUTOCHECKPOINT SQLITE_BUSY_TIMEOUT_MS SQLITE_WAL_CHECKPOINT SHUTDOWN_TIMEOUT_S SHUTDOWN_TIMEOUT_TEST_S QUEUE_TIMEOUT_S QUEUE_TIMEOUT_TEST_S CIRCUIT_BREAKER_FAILURE_THRESHOLD CIRCUIT_BREAKER_RECOVERY_TIMEOUT_S CIRCUIT_BREAKER_HALF_OPEN_MAX_CALLS POSTGRESQL_CONNECTION_STRING POSTGRESQL_HOST POSTGRESQL_PORT POSTGRESQL_USER POSTGRESQL_PASSWORD POSTGRESQL_DATABASE POSTGRESQL_POOL_MIN POSTGRESQL_POOL_MAX POSTGRESQL_POOL_TIMEOUT_S POSTGRESQL_COMMAND_TIMEOUT_S POSTGRESQL_MIGRATION_TIMEOUT_S POSTGRESQL_MAX_INACTIVE_LIFETIME_S POSTGRESQL_MAX_QUERIES POSTGRESQL_TCP_KEEPALIVES_IDLE_S POSTGRESQL_TCP_KEEPALIVES_INTERVAL_S POSTGRESQL_TCP_KEEPALIVES_COUNT POSTGRESQL_STATEMENT_CACHE_SIZE POSTGRESQL_MAX_CACHED_STATEMENT_LIFETIME_S POSTGRESQL_MAX_CACHEABLE_STATEMENT_SIZE POSTGRESQL_SSL_MODE POSTGRESQL_SCHEMA ENABLE_SEMANTIC_SEARCH ENABLE_EMBEDDING_GENERATION OLLAMA_HOST OLLAMA_AUTO_PULL OLLAMA_PULL_TIMEOUT_S EMBEDDING_OLLAMA_TRUNCATE EMBEDDING_OLLAMA_NUM_CTX EMBEDDING_MODEL EMBEDDING_DIM EMBEDDING_TIMEOUT_S EMBEDDING_RETRY_MAX_ATTEMPTS EMBEDDING_RETRY_BASE_DELAY_S EMBEDDING_MAX_CONCURRENT ENABLE_SUMMARY_GENERATION SUMMARY_PROVIDER SUMMARY_MODEL SUMMARY_MAX_TOKENS SUMMARY_TIMEOUT_S SUMMARY_RETRY_MAX_ATTEMPTS SUMMARY_RETRY_BASE_DELAY_S SUMMARY_MAX_CONCURRENT SUMMARY_PROMPT SUMMARY_MIN_CONTENT_LENGTH SUMMARY_OLLAMA_NUM_CTX SUMMARY_OLLAMA_TRUNCATE SUMMARY_OPENAI_REASONING_EFFORT SUMMARY_ANTHROPIC_EFFORT ANTHROPIC_API_KEY ENABLE_FTS FTS_LANGUAGE FTS_RERANK_WINDOW_SIZE FTS_RERANK_GAP_MERGE ENABLE_HYBRID_SEARCH HYBRID_RRF_K HYBRID_RRF_OVERFETCH HYBRID_FTS_OR_THRESHOLD SEARCH_DEFAULT_SORT_BY SEARCH_TRUNCATION_LENGTH ENABLE_CHUNKING CHUNK_SIZE CHUNK_OVERLAP CHUNK_AGGREGATION CHUNK_DEDUP_OVERFETCH ENABLE_RERANKING RERANKING_PROVIDER RERANKING_MODEL RERANKING_MAX_LENGTH RERANKING_OVERFETCH RERANKING_CACHE_DIR RERANKING_CHARS_PER_TOKEN RERANKING_INTRA_OP_THREADS RERANKING_CPU_MEM_ARENA RERANKING_BATCH_SIZE EMBEDDING_PROVIDER OPENAI_API_KEY OPENAI_API_BASE OPENAI_ORGANIZATION AZURE_OPENAI_API_KEY AZURE_OPENAI_ENDPOINT AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME AZURE_OPENAI_API_VERSION HUGGINGFACEHUB_API_TOKEN VOYAGE_API_KEY VOYAGE_TRUNCATION VOYAGE_BATCH_SIZE LANGSMITH_TRACING LANGSMITH_API_KEY LANGSMITH_PROJECT LANGSMITH_ENDPOINT METADATA_INDEXED_FIELDS METADATA_INDEX_SYNC_MODE MCP_TRANSPORT FASTMCP_HOST FASTMCP_PORT FASTMCP_STATELESS_HTTP DISABLED_TOOLS MCP_AUTH_TOKEN MCP_AUTH_CLIENT_ID MCP_AUTH_PROVIDER MCP_SERVER_INSTRUCTIONS

AI and LLMs Files and storage

Setup snippets

Generated from the registry entry. cosmic-mcp has not run or reviewed this server; values in angle brackets are yours to fill in.

Run it locally (pypi)

uvx 'mcp-context-server==2.2.2'

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "mcp-context-server": {
      "args": [
        "mcp-context-server==2.2.2"
      ],
      "command": "uvx",
      "env": {
        "ANTHROPIC_API_KEY": "<your anthropic api key>",
        "AZURE_OPENAI_API_KEY": "<your azure openai api key>",
        "AZURE_OPENAI_API_VERSION": "<your azure openai api version>",
        "AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME": "<your azure openai embedding deployment name>",
        "AZURE_OPENAI_ENDPOINT": "<your azure openai endpoint>",
        "CHUNK_AGGREGATION": "<your chunk aggregation>",
        "CHUNK_DEDUP_OVERFETCH": "<your chunk dedup overfetch>",
        "CHUNK_OVERLAP": "<your chunk overlap>",
        "CHUNK_SIZE": "<your chunk size>",
        "CIRCUIT_BREAKER_FAILURE_THRESHOLD": "<your circuit breaker failure threshold>",
        "CIRCUIT_BREAKER_HALF_OPEN_MAX_CALLS": "<your circuit breaker half open max calls>",
        "CIRCUIT_BREAKER_RECOVERY_TIMEOUT_S": "<your circuit breaker recovery timeout s>",
        "DB_PATH": "<your db path>",
        "DISABLED_TOOLS": "<your disabled tools>",
        "EMBEDDING_DIM": "<your embedding dim>",
        "EMBEDDING_MAX_CONCURRENT": "<your embedding max concurrent>",
        "EMBEDDING_MODEL": "<your embedding model>",
        "EMBEDDING_OLLAMA_NUM_CTX": "<your embedding ollama num ctx>",
        "EMBEDDING_OLLAMA_TRUNCATE": "<your embedding ollama truncate>",
        "EMBEDDING_PROVIDER": "<your embedding provider>",
        "EMBEDDING_RETRY_BASE_DELAY_S": "<your embedding retry base delay s>",
        "EMBEDDING_RETRY_MAX_ATTEMPTS": "<your embedding retry max attempts>",
        "EMBEDDING_TIMEOUT_S": "<your embedding timeout s>",
        "ENABLE_CHUNKING": "<your enable chunking>",
        "ENABLE_EMBEDDING_GENERATION": "<your enable embedding generation>",
        "ENABLE_FTS": "<your enable fts>",
        "ENABLE_HYBRID_SEARCH": "<your enable hybrid search>",
        "ENABLE_RERANKING": "<your enable reranking>",
        "ENABLE_SEMANTIC_SEARCH": "<your enable semantic search>",
        "ENABLE_SUMMARY_GENERATION": "<your enable summary generation>",
        "FASTMCP_HOST": "<your fastmcp host>",
        "FASTMCP_PORT": "<your fastmcp port>",
        "FASTMCP_STATELESS_HTTP": "<your fastmcp stateless http>",
        "FTS_LANGUAGE": "<your fts language>",
        "FTS_RERANK_GAP_MERGE": "<your fts rerank gap merge>",
        "FTS_RERANK_WINDOW_SIZE": "<your fts rerank window size>",
        "HUGGINGFACEHUB_API_TOKEN": "<your huggingfacehub api token>",
        "HYBRID_FTS_OR_THRESHOLD": "<your hybrid fts or threshold>",
        "HYBRID_RRF_K": "<your hybrid rrf k>",
        "HYBRID_RRF_OVERFETCH": "<your hybrid rrf overfetch>",
        "LANGSMITH_API_KEY": "<your langsmith api key>",
        "LANGSMITH_ENDPOINT": "<your langsmith endpoint>",
        "LANGSMITH_PROJECT": "<your langsmith project>",
        "LANGSMITH_TRACING": "<your langsmith tracing>",
        "LOG_LEVEL": "<your log level>",
        "MAX_IMAGE_SIZE_MB": "<your max image size mb>",
        "MAX_TOTAL_SIZE_MB": "<your max total size mb>",
        "MCP_AUTH_CLIENT_ID": "<your mcp auth client id>",
        "MCP_AUTH_PROVIDER": "<your mcp auth provider>",
        "MCP_AUTH_TOKEN": "<your mcp auth token>",
        "MCP_SERVER_INSTRUCTIONS": "<your mcp server instructions>",
        "MCP_TRANSPORT": "<your mcp transport>",
        "METADATA_INDEXED_FIELDS": "<your metadata indexed fields>",
        "METADATA_INDEX_SYNC_MODE": "<your metadata index sync mode>",
        "OLLAMA_AUTO_PULL": "<your ollama auto pull>",
        "OLLAMA_HOST": "<your ollama host>",
        "OLLAMA_PULL_TIMEOUT_S": "<your ollama pull timeout s>",
        "OPENAI_API_BASE": "<your openai api base>",
        "OPENAI_API_KEY": "<your openai api key>",
        "OPENAI_ORGANIZATION": "<your openai organization>",
        "POOL_CONNECTION_TIMEOUT_S": "<your pool connection timeout s>",
        "POOL_HEALTH_CHECK_INTERVAL_S": "<your pool health check interval s>",
        "POOL_IDLE_TIMEOUT_S": "<your pool idle timeout s>",
        "POOL_MAX_READERS": "<your pool max readers>",
        "POOL_MAX_WRITERS": "<your pool max writers>",
        "POSTGRESQL_COMMAND_TIMEOUT_S": "<your postgresql command timeout s>",
        "POSTGRESQL_CONNECTION_STRING": "<your postgresql connection string>",
        "POSTGRESQL_DATABASE": "<your postgresql database>",
        "POSTGRESQL_HOST": "<your postgresql host>",
        "POSTGRESQL_MAX_CACHEABLE_STATEMENT_SIZE": "<your postgresql max cacheable statement size>",
        "POSTGRESQL_MAX_CACHED_STATEMENT_LIFETIME_S": "<your postgresql max cached statement lifetime s>",
        "POSTGRESQL_MAX_INACTIVE_LIFETIME_S": "<your postgresql max inactive lifetime s>",
        "POSTGRESQL_MAX_QUERIES": "<your postgresql max queries>",
        "POSTGRESQL_MIGRATION_TIMEOUT_S": "<your postgresql migration timeout s>",
        "POSTGRESQL_PASSWORD": "<your postgresql password>",
        "POSTGRESQL_POOL_MAX": "<your postgresql pool max>",
        "POSTGRESQL_POOL_MIN": "<your postgresql pool min>",
        "POSTGRESQL_POOL_TIMEOUT_S": "<your postgresql pool timeout s>",
        "POSTGRESQL_PORT": "<your postgresql port>",
        "POSTGRESQL_SCHEMA": "<your postgresql schema>",
        "POSTGRESQL_SSL_MODE": "<your postgresql ssl mode>",
        "POSTGRESQL_STATEMENT_CACHE_SIZE": "<your postgresql statement cache size>",
        "POSTGRESQL_TCP_KEEPALIVES_COUNT": "<your postgresql tcp keepalives count>",
        "POSTGRESQL_TCP_KEEPALIVES_IDLE_S": "<your postgresql tcp keepalives idle s>",
        "POSTGRESQL_TCP_KEEPALIVES_INTERVAL_S": "<your postgresql tcp keepalives interval s>",
        "POSTGRESQL_USER": "<your postgresql user>",
        "QUEUE_TIMEOUT_S": "<your queue timeout s>",
        "QUEUE_TIMEOUT_TEST_S": "<your queue timeout test s>",
        "RERANKING_BATCH_SIZE": "<your reranking batch size>",
        "RERANKING_CACHE_DIR": "<your reranking cache dir>",
        "RERANKING_CHARS_PER_TOKEN": "<your reranking chars per token>",
        "RERANKING_CPU_MEM_ARENA": "<your reranking cpu mem arena>",
        "RERANKING_INTRA_OP_THREADS": "<your reranking intra op threads>",
        "RERANKING_MAX_LENGTH": "<your reranking max length>",
        "RERANKING_MODEL": "<your reranking model>",
        "RERANKING_OVERFETCH": "<your reranking overfetch>",
        "RERANKING_PROVIDER": "<your reranking provider>",
        "RETRY_BACKOFF_FACTOR": "<your retry backoff factor>",
        "RETRY_BASE_DELAY_S": "<your retry base delay s>",
        "RETRY_JITTER": "<your retry jitter>",
        "RETRY_MAX_DELAY_S": "<your retry max delay s>",
        "RETRY_MAX_RETRIES": "<your retry max retries>",
        "SEARCH_DEFAULT_SORT_BY": "<your search default sort by>",
        "SEARCH_TRUNCATION_LENGTH": "<your search truncation length>",
        "SHUTDOWN_TIMEOUT_S": "<your shutdown timeout s>",
        "SHUTDOWN_TIMEOUT_TEST_S": "<your shutdown timeout test s>",
        "SQLITE_BUSY_TIMEOUT_MS": "<your sqlite busy timeout ms>",
        "SQLITE_CACHE_SIZE": "<your sqlite cache size>",
        "SQLITE_FOREIGN_KEYS": "<your sqlite foreign keys>",
        "SQLITE_JOURNAL_MODE": "<your sqlite journal mode>",
        "SQLITE_MMAP_SIZE": "<your sqlite mmap size>",
        "SQLITE_PAGE_SIZE": "<your sqlite page size>",
        "SQLITE_SYNCHRONOUS": "<your sqlite synchronous>",
        "SQLITE_TEMP_STORE": "<your sqlite temp store>",
        "SQLITE_WAL_AUTOCHECKPOINT": "<your sqlite wal autocheckpoint>",
        "SQLITE_WAL_CHECKPOINT": "<your sqlite wal checkpoint>",
        "STORAGE_BACKEND": "<your storage backend>",
        "SUMMARY_ANTHROPIC_EFFORT": "<your summary anthropic effort>",
        "SUMMARY_MAX_CONCURRENT": "<your summary max concurrent>",
        "SUMMARY_MAX_TOKENS": "<your summary max tokens>",
        "SUMMARY_MIN_CONTENT_LENGTH": "<your summary min content length>",
        "SUMMARY_MODEL": "<your summary model>",
        "SUMMARY_OLLAMA_NUM_CTX": "<your summary ollama num ctx>",
        "SUMMARY_OLLAMA_TRUNCATE": "<your summary ollama truncate>",
        "SUMMARY_OPENAI_REASONING_EFFORT": "<your summary openai reasoning effort>",
        "SUMMARY_PROMPT": "<your summary prompt>",
        "SUMMARY_PROVIDER": "<your summary provider>",
        "SUMMARY_RETRY_BASE_DELAY_S": "<your summary retry base delay s>",
        "SUMMARY_RETRY_MAX_ATTEMPTS": "<your summary retry max attempts>",
        "SUMMARY_TIMEOUT_S": "<your summary timeout s>",
        "VOYAGE_API_KEY": "<your voyage api key>",
        "VOYAGE_BATCH_SIZE": "<your voyage batch size>",
        "VOYAGE_TRUNCATION": "<your voyage truncation>"
      }
    }
  }
}

Claude Code

claude mcp add 'mcp-context-server' -- uvx 'mcp-context-server==2.2.2'

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "mcp-context-server": {
      "args": [
        "mcp-context-server==2.2.2"
      ],
      "command": "uvx",
      "env": {
        "ANTHROPIC_API_KEY": "<your anthropic api key>",
        "AZURE_OPENAI_API_KEY": "<your azure openai api key>",
        "AZURE_OPENAI_API_VERSION": "<your azure openai api version>",
        "AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME": "<your azure openai embedding deployment name>",
        "AZURE_OPENAI_ENDPOINT": "<your azure openai endpoint>",
        "CHUNK_AGGREGATION": "<your chunk aggregation>",
        "CHUNK_DEDUP_OVERFETCH": "<your chunk dedup overfetch>",
        "CHUNK_OVERLAP": "<your chunk overlap>",
        "CHUNK_SIZE": "<your chunk size>",
        "CIRCUIT_BREAKER_FAILURE_THRESHOLD": "<your circuit breaker failure threshold>",
        "CIRCUIT_BREAKER_HALF_OPEN_MAX_CALLS": "<your circuit breaker half open max calls>",
        "CIRCUIT_BREAKER_RECOVERY_TIMEOUT_S": "<your circuit breaker recovery timeout s>",
        "DB_PATH": "<your db path>",
        "DISABLED_TOOLS": "<your disabled tools>",
        "EMBEDDING_DIM": "<your embedding dim>",
        "EMBEDDING_MAX_CONCURRENT": "<your embedding max concurrent>",
        "EMBEDDING_MODEL": "<your embedding model>",
        "EMBEDDING_OLLAMA_NUM_CTX": "<your embedding ollama num ctx>",
        "EMBEDDING_OLLAMA_TRUNCATE": "<your embedding ollama truncate>",
        "EMBEDDING_PROVIDER": "<your embedding provider>",
        "EMBEDDING_RETRY_BASE_DELAY_S": "<your embedding retry base delay s>",
        "EMBEDDING_RETRY_MAX_ATTEMPTS": "<your embedding retry max attempts>",
        "EMBEDDING_TIMEOUT_S": "<your embedding timeout s>",
        "ENABLE_CHUNKING": "<your enable chunking>",
        "ENABLE_EMBEDDING_GENERATION": "<your enable embedding generation>",
        "ENABLE_FTS": "<your enable fts>",
        "ENABLE_HYBRID_SEARCH": "<your enable hybrid search>",
        "ENABLE_RERANKING": "<your enable reranking>",
        "ENABLE_SEMANTIC_SEARCH": "<your enable semantic search>",
        "ENABLE_SUMMARY_GENERATION": "<your enable summary generation>",
        "FASTMCP_HOST": "<your fastmcp host>",
        "FASTMCP_PORT": "<your fastmcp port>",
        "FASTMCP_STATELESS_HTTP": "<your fastmcp stateless http>",
        "FTS_LANGUAGE": "<your fts language>",
        "FTS_RERANK_GAP_MERGE": "<your fts rerank gap merge>",
        "FTS_RERANK_WINDOW_SIZE": "<your fts rerank window size>",
        "HUGGINGFACEHUB_API_TOKEN": "<your huggingfacehub api token>",
        "HYBRID_FTS_OR_THRESHOLD": "<your hybrid fts or threshold>",
        "HYBRID_RRF_K": "<your hybrid rrf k>",
        "HYBRID_RRF_OVERFETCH": "<your hybrid rrf overfetch>",
        "LANGSMITH_API_KEY": "<your langsmith api key>",
        "LANGSMITH_ENDPOINT": "<your langsmith endpoint>",
        "LANGSMITH_PROJECT": "<your langsmith project>",
        "LANGSMITH_TRACING": "<your langsmith tracing>",
        "LOG_LEVEL": "<your log level>",
        "MAX_IMAGE_SIZE_MB": "<your max image size mb>",
        "MAX_TOTAL_SIZE_MB": "<your max total size mb>",
        "MCP_AUTH_CLIENT_ID": "<your mcp auth client id>",
        "MCP_AUTH_PROVIDER": "<your mcp auth provider>",
        "MCP_AUTH_TOKEN": "<your mcp auth token>",
        "MCP_SERVER_INSTRUCTIONS": "<your mcp server instructions>",
        "MCP_TRANSPORT": "<your mcp transport>",
        "METADATA_INDEXED_FIELDS": "<your metadata indexed fields>",
        "METADATA_INDEX_SYNC_MODE": "<your metadata index sync mode>",
        "OLLAMA_AUTO_PULL": "<your ollama auto pull>",
        "OLLAMA_HOST": "<your ollama host>",
        "OLLAMA_PULL_TIMEOUT_S": "<your ollama pull timeout s>",
        "OPENAI_API_BASE": "<your openai api base>",
        "OPENAI_API_KEY": "<your openai api key>",
        "OPENAI_ORGANIZATION": "<your openai organization>",
        "POOL_CONNECTION_TIMEOUT_S": "<your pool connection timeout s>",
        "POOL_HEALTH_CHECK_INTERVAL_S": "<your pool health check interval s>",
        "POOL_IDLE_TIMEOUT_S": "<your pool idle timeout s>",
        "POOL_MAX_READERS": "<your pool max readers>",
        "POOL_MAX_WRITERS": "<your pool max writers>",
        "POSTGRESQL_COMMAND_TIMEOUT_S": "<your postgresql command timeout s>",
        "POSTGRESQL_CONNECTION_STRING": "<your postgresql connection string>",
        "POSTGRESQL_DATABASE": "<your postgresql database>",
        "POSTGRESQL_HOST": "<your postgresql host>",
        "POSTGRESQL_MAX_CACHEABLE_STATEMENT_SIZE": "<your postgresql max cacheable statement size>",
        "POSTGRESQL_MAX_CACHED_STATEMENT_LIFETIME_S": "<your postgresql max cached statement lifetime s>",
        "POSTGRESQL_MAX_INACTIVE_LIFETIME_S": "<your postgresql max inactive lifetime s>",
        "POSTGRESQL_MAX_QUERIES": "<your postgresql max queries>",
        "POSTGRESQL_MIGRATION_TIMEOUT_S": "<your postgresql migration timeout s>",
        "POSTGRESQL_PASSWORD": "<your postgresql password>",
        "POSTGRESQL_POOL_MAX": "<your postgresql pool max>",
        "POSTGRESQL_POOL_MIN": "<your postgresql pool min>",
        "POSTGRESQL_POOL_TIMEOUT_S": "<your postgresql pool timeout s>",
        "POSTGRESQL_PORT": "<your postgresql port>",
        "POSTGRESQL_SCHEMA": "<your postgresql schema>",
        "POSTGRESQL_SSL_MODE": "<your postgresql ssl mode>",
        "POSTGRESQL_STATEMENT_CACHE_SIZE": "<your postgresql statement cache size>",
        "POSTGRESQL_TCP_KEEPALIVES_COUNT": "<your postgresql tcp keepalives count>",
        "POSTGRESQL_TCP_KEEPALIVES_IDLE_S": "<your postgresql tcp keepalives idle s>",
        "POSTGRESQL_TCP_KEEPALIVES_INTERVAL_S": "<your postgresql tcp keepalives interval s>",
        "POSTGRESQL_USER": "<your postgresql user>",
        "QUEUE_TIMEOUT_S": "<your queue timeout s>",
        "QUEUE_TIMEOUT_TEST_S": "<your queue timeout test s>",
        "RERANKING_BATCH_SIZE": "<your reranking batch size>",
        "RERANKING_CACHE_DIR": "<your reranking cache dir>",
        "RERANKING_CHARS_PER_TOKEN": "<your reranking chars per token>",
        "RERANKING_CPU_MEM_ARENA": "<your reranking cpu mem arena>",
        "RERANKING_INTRA_OP_THREADS": "<your reranking intra op threads>",
        "RERANKING_MAX_LENGTH": "<your reranking max length>",
        "RERANKING_MODEL": "<your reranking model>",
        "RERANKING_OVERFETCH": "<your reranking overfetch>",
        "RERANKING_PROVIDER": "<your reranking provider>",
        "RETRY_BACKOFF_FACTOR": "<your retry backoff factor>",
        "RETRY_BASE_DELAY_S": "<your retry base delay s>",
        "RETRY_JITTER": "<your retry jitter>",
        "RETRY_MAX_DELAY_S": "<your retry max delay s>",
        "RETRY_MAX_RETRIES": "<your retry max retries>",
        "SEARCH_DEFAULT_SORT_BY": "<your search default sort by>",
        "SEARCH_TRUNCATION_LENGTH": "<your search truncation length>",
        "SHUTDOWN_TIMEOUT_S": "<your shutdown timeout s>",
        "SHUTDOWN_TIMEOUT_TEST_S": "<your shutdown timeout test s>",
        "SQLITE_BUSY_TIMEOUT_MS": "<your sqlite busy timeout ms>",
        "SQLITE_CACHE_SIZE": "<your sqlite cache size>",
        "SQLITE_FOREIGN_KEYS": "<your sqlite foreign keys>",
        "SQLITE_JOURNAL_MODE": "<your sqlite journal mode>",
        "SQLITE_MMAP_SIZE": "<your sqlite mmap size>",
        "SQLITE_PAGE_SIZE": "<your sqlite page size>",
        "SQLITE_SYNCHRONOUS": "<your sqlite synchronous>",
        "SQLITE_TEMP_STORE": "<your sqlite temp store>",
        "SQLITE_WAL_AUTOCHECKPOINT": "<your sqlite wal autocheckpoint>",
        "SQLITE_WAL_CHECKPOINT": "<your sqlite wal checkpoint>",
        "STORAGE_BACKEND": "<your storage backend>",
        "SUMMARY_ANTHROPIC_EFFORT": "<your summary anthropic effort>",
        "SUMMARY_MAX_CONCURRENT": "<your summary max concurrent>",
        "SUMMARY_MAX_TOKENS": "<your summary max tokens>",
        "SUMMARY_MIN_CONTENT_LENGTH": "<your summary min content length>",
        "SUMMARY_MODEL": "<your summary model>",
        "SUMMARY_OLLAMA_NUM_CTX": "<your summary ollama num ctx>",
        "SUMMARY_OLLAMA_TRUNCATE": "<your summary ollama truncate>",
        "SUMMARY_OPENAI_REASONING_EFFORT": "<your summary openai reasoning effort>",
        "SUMMARY_PROMPT": "<your summary prompt>",
        "SUMMARY_PROVIDER": "<your summary provider>",
        "SUMMARY_RETRY_BASE_DELAY_S": "<your summary retry base delay s>",
        "SUMMARY_RETRY_MAX_ATTEMPTS": "<your summary retry max attempts>",
        "SUMMARY_TIMEOUT_S": "<your summary timeout s>",
        "VOYAGE_API_KEY": "<your voyage api key>",
        "VOYAGE_BATCH_SIZE": "<your voyage batch size>",
        "VOYAGE_TRUNCATION": "<your voyage truncation>"
      }
    }
  }
}

VS Code (.vscode/mcp.json)

{
  "servers": {
    "mcp-context-server": {
      "args": [
        "mcp-context-server==2.2.2"
      ],
      "command": "uvx",
      "env": {
        "ANTHROPIC_API_KEY": "<your anthropic api key>",
        "AZURE_OPENAI_API_KEY": "<your azure openai api key>",
        "AZURE_OPENAI_API_VERSION": "<your azure openai api version>",
        "AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME": "<your azure openai embedding deployment name>",
        "AZURE_OPENAI_ENDPOINT": "<your azure openai endpoint>",
        "CHUNK_AGGREGATION": "<your chunk aggregation>",
        "CHUNK_DEDUP_OVERFETCH": "<your chunk dedup overfetch>",
        "CHUNK_OVERLAP": "<your chunk overlap>",
        "CHUNK_SIZE": "<your chunk size>",
        "CIRCUIT_BREAKER_FAILURE_THRESHOLD": "<your circuit breaker failure threshold>",
        "CIRCUIT_BREAKER_HALF_OPEN_MAX_CALLS": "<your circuit breaker half open max calls>",
        "CIRCUIT_BREAKER_RECOVERY_TIMEOUT_S": "<your circuit breaker recovery timeout s>",
        "DB_PATH": "<your db path>",
        "DISABLED_TOOLS": "<your disabled tools>",
        "EMBEDDING_DIM": "<your embedding dim>",
        "EMBEDDING_MAX_CONCURRENT": "<your embedding max concurrent>",
        "EMBEDDING_MODEL": "<your embedding model>",
        "EMBEDDING_OLLAMA_NUM_CTX": "<your embedding ollama num ctx>",
        "EMBEDDING_OLLAMA_TRUNCATE": "<your embedding ollama truncate>",
        "EMBEDDING_PROVIDER": "<your embedding provider>",
        "EMBEDDING_RETRY_BASE_DELAY_S": "<your embedding retry base delay s>",
        "EMBEDDING_RETRY_MAX_ATTEMPTS": "<your embedding retry max attempts>",
        "EMBEDDING_TIMEOUT_S": "<your embedding timeout s>",
        "ENABLE_CHUNKING": "<your enable chunking>",
        "ENABLE_EMBEDDING_GENERATION": "<your enable embedding generation>",
        "ENABLE_FTS": "<your enable fts>",
        "ENABLE_HYBRID_SEARCH": "<your enable hybrid search>",
        "ENABLE_RERANKING": "<your enable reranking>",
        "ENABLE_SEMANTIC_SEARCH": "<your enable semantic search>",
        "ENABLE_SUMMARY_GENERATION": "<your enable summary generation>",
        "FASTMCP_HOST": "<your fastmcp host>",
        "FASTMCP_PORT": "<your fastmcp port>",
        "FASTMCP_STATELESS_HTTP": "<your fastmcp stateless http>",
        "FTS_LANGUAGE": "<your fts language>",
        "FTS_RERANK_GAP_MERGE": "<your fts rerank gap merge>",
        "FTS_RERANK_WINDOW_SIZE": "<your fts rerank window size>",
        "HUGGINGFACEHUB_API_TOKEN": "<your huggingfacehub api token>",
        "HYBRID_FTS_OR_THRESHOLD": "<your hybrid fts or threshold>",
        "HYBRID_RRF_K": "<your hybrid rrf k>",
        "HYBRID_RRF_OVERFETCH": "<your hybrid rrf overfetch>",
        "LANGSMITH_API_KEY": "<your langsmith api key>",
        "LANGSMITH_ENDPOINT": "<your langsmith endpoint>",
        "LANGSMITH_PROJECT": "<your langsmith project>",
        "LANGSMITH_TRACING": "<your langsmith tracing>",
        "LOG_LEVEL": "<your log level>",
        "MAX_IMAGE_SIZE_MB": "<your max image size mb>",
        "MAX_TOTAL_SIZE_MB": "<your max total size mb>",
        "MCP_AUTH_CLIENT_ID": "<your mcp auth client id>",
        "MCP_AUTH_PROVIDER": "<your mcp auth provider>",
        "MCP_AUTH_TOKEN": "<your mcp auth token>",
        "MCP_SERVER_INSTRUCTIONS": "<your mcp server instructions>",
        "MCP_TRANSPORT": "<your mcp transport>",
        "METADATA_INDEXED_FIELDS": "<your metadata indexed fields>",
        "METADATA_INDEX_SYNC_MODE": "<your metadata index sync mode>",
        "OLLAMA_AUTO_PULL": "<your ollama auto pull>",
        "OLLAMA_HOST": "<your ollama host>",
        "OLLAMA_PULL_TIMEOUT_S": "<your ollama pull timeout s>",
        "OPENAI_API_BASE": "<your openai api base>",
        "OPENAI_API_KEY": "<your openai api key>",
        "OPENAI_ORGANIZATION": "<your openai organization>",
        "POOL_CONNECTION_TIMEOUT_S": "<your pool connection timeout s>",
        "POOL_HEALTH_CHECK_INTERVAL_S": "<your pool health check interval s>",
        "POOL_IDLE_TIMEOUT_S": "<your pool idle timeout s>",
        "POOL_MAX_READERS": "<your pool max readers>",
        "POOL_MAX_WRITERS": "<your pool max writers>",
        "POSTGRESQL_COMMAND_TIMEOUT_S": "<your postgresql command timeout s>",
        "POSTGRESQL_CONNECTION_STRING": "<your postgresql connection string>",
        "POSTGRESQL_DATABASE": "<your postgresql database>",
        "POSTGRESQL_HOST": "<your postgresql host>",
        "POSTGRESQL_MAX_CACHEABLE_STATEMENT_SIZE": "<your postgresql max cacheable statement size>",
        "POSTGRESQL_MAX_CACHED_STATEMENT_LIFETIME_S": "<your postgresql max cached statement lifetime s>",
        "POSTGRESQL_MAX_INACTIVE_LIFETIME_S": "<your postgresql max inactive lifetime s>",
        "POSTGRESQL_MAX_QUERIES": "<your postgresql max queries>",
        "POSTGRESQL_MIGRATION_TIMEOUT_S": "<your postgresql migration timeout s>",
        "POSTGRESQL_PASSWORD": "<your postgresql password>",
        "POSTGRESQL_POOL_MAX": "<your postgresql pool max>",
        "POSTGRESQL_POOL_MIN": "<your postgresql pool min>",
        "POSTGRESQL_POOL_TIMEOUT_S": "<your postgresql pool timeout s>",
        "POSTGRESQL_PORT": "<your postgresql port>",
        "POSTGRESQL_SCHEMA": "<your postgresql schema>",
        "POSTGRESQL_SSL_MODE": "<your postgresql ssl mode>",
        "POSTGRESQL_STATEMENT_CACHE_SIZE": "<your postgresql statement cache size>",
        "POSTGRESQL_TCP_KEEPALIVES_COUNT": "<your postgresql tcp keepalives count>",
        "POSTGRESQL_TCP_KEEPALIVES_IDLE_S": "<your postgresql tcp keepalives idle s>",
        "POSTGRESQL_TCP_KEEPALIVES_INTERVAL_S": "<your postgresql tcp keepalives interval s>",
        "POSTGRESQL_USER": "<your postgresql user>",
        "QUEUE_TIMEOUT_S": "<your queue timeout s>",
        "QUEUE_TIMEOUT_TEST_S": "<your queue timeout test s>",
        "RERANKING_BATCH_SIZE": "<your reranking batch size>",
        "RERANKING_CACHE_DIR": "<your reranking cache dir>",
        "RERANKING_CHARS_PER_TOKEN": "<your reranking chars per token>",
        "RERANKING_CPU_MEM_ARENA": "<your reranking cpu mem arena>",
        "RERANKING_INTRA_OP_THREADS": "<your reranking intra op threads>",
        "RERANKING_MAX_LENGTH": "<your reranking max length>",
        "RERANKING_MODEL": "<your reranking model>",
        "RERANKING_OVERFETCH": "<your reranking overfetch>",
        "RERANKING_PROVIDER": "<your reranking provider>",
        "RETRY_BACKOFF_FACTOR": "<your retry backoff factor>",
        "RETRY_BASE_DELAY_S": "<your retry base delay s>",
        "RETRY_JITTER": "<your retry jitter>",
        "RETRY_MAX_DELAY_S": "<your retry max delay s>",
        "RETRY_MAX_RETRIES": "<your retry max retries>",
        "SEARCH_DEFAULT_SORT_BY": "<your search default sort by>",
        "SEARCH_TRUNCATION_LENGTH": "<your search truncation length>",
        "SHUTDOWN_TIMEOUT_S": "<your shutdown timeout s>",
        "SHUTDOWN_TIMEOUT_TEST_S": "<your shutdown timeout test s>",
        "SQLITE_BUSY_TIMEOUT_MS": "<your sqlite busy timeout ms>",
        "SQLITE_CACHE_SIZE": "<your sqlite cache size>",
        "SQLITE_FOREIGN_KEYS": "<your sqlite foreign keys>",
        "SQLITE_JOURNAL_MODE": "<your sqlite journal mode>",
        "SQLITE_MMAP_SIZE": "<your sqlite mmap size>",
        "SQLITE_PAGE_SIZE": "<your sqlite page size>",
        "SQLITE_SYNCHRONOUS": "<your sqlite synchronous>",
        "SQLITE_TEMP_STORE": "<your sqlite temp store>",
        "SQLITE_WAL_AUTOCHECKPOINT": "<your sqlite wal autocheckpoint>",
        "SQLITE_WAL_CHECKPOINT": "<your sqlite wal checkpoint>",
        "STORAGE_BACKEND": "<your storage backend>",
        "SUMMARY_ANTHROPIC_EFFORT": "<your summary anthropic effort>",
        "SUMMARY_MAX_CONCURRENT": "<your summary max concurrent>",
        "SUMMARY_MAX_TOKENS": "<your summary max tokens>",
        "SUMMARY_MIN_CONTENT_LENGTH": "<your summary min content length>",
        "SUMMARY_MODEL": "<your summary model>",
        "SUMMARY_OLLAMA_NUM_CTX": "<your summary ollama num ctx>",
        "SUMMARY_OLLAMA_TRUNCATE": "<your summary ollama truncate>",
        "SUMMARY_OPENAI_REASONING_EFFORT": "<your summary openai reasoning effort>",
        "SUMMARY_PROMPT": "<your summary prompt>",
        "SUMMARY_PROVIDER": "<your summary provider>",
        "SUMMARY_RETRY_BASE_DELAY_S": "<your summary retry base delay s>",
        "SUMMARY_RETRY_MAX_ATTEMPTS": "<your summary retry max attempts>",
        "SUMMARY_TIMEOUT_S": "<your summary timeout s>",
        "VOYAGE_API_KEY": "<your voyage api key>",
        "VOYAGE_BATCH_SIZE": "<your voyage batch size>",
        "VOYAGE_TRUNCATION": "<your voyage truncation>"
      },
      "type": "stdio"
    }
  }
}

Related servers

  • Harness Verified domain
    Start Claude Code and Codex agents the person can watch, wait for them and read their answers.
  • docs-mcp Verified domain
    Remote MCP server for Tandem docs, install guides, SDKs, workflows, and agent setup help.
  • spotdb Verified domain
    Ephemeral data sandbox for AI workflows with guardrails and security
  • Adako: ad ops for AI assistants Verified domain
    Google, Meta, LinkedIn and ChatGPT Ads for AI assistants. Every change needs your approval.
  • Aidoo for Odoo Verified domain
    Query and update your Odoo ERP in plain language, under your own Odoo access rules.
  • EXTREMELY agency Verified domain
    Your agency of AI agents in your AI app: what agents did, approvals, requests, jobs and reports.