Context MCP server

by alex-feel·io.github.alex-feel/mcp-context-server·v2.2.2·9 stars

No reviews yet

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

B83/100grade B

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

B83/100

full report

Adoption

Growing

9 stars67 downloads/wk

Reviews

Write one

Nobody has reviewed Context yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Context tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings

Code scan113 source files scanned25/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitystatic API keys via environment variables6/15
Maintenancelast push 0 days ago15/15
Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How Context compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 83/100; higher than 68% of 4,460 AI and agents servers
GitHub stars: 9; more than 83% of 2,711 AI and agents servers
Downloads a week: 67; more than 53% of 1,538 AI and agents servers with a package

Install Context in Claude Code, Cursor or VS Code

claude mcp add mcp-context-server -- uvx mcp-context-server

Add to Cursor

What the publisher says

From the Context repository's README, as published. We do not edit it. Read it on GitHub

MCP Context Server

A high-performance Model Context Protocol (MCP) server providing persistent multimodal context storage for LLM agents. Built with FastMCP, this server enables seamless context sharing across multiple agents working on the same task through thread-based scoping.

[!WARNING]

Upgrading from v2.x? Version 3.x.x uses a new database schema with UUIDv7 primary keys. Existing v2.x databases require a one-time data migration before they can be used with v3.x.x. The opt-in CLI mcp-context-server-migrate ships with the server.

See the Migration Guide before upgrading. Fresh installations are unaffected.

Key Features

Multimodal Context Storage: Store and retrieve both text and images
UUIDv7 Context Identifiers: Every context entry is identified by a 32-character lowercase hex UUIDv7 value, providing time-ordered, globally unique IDs with a stable lex-string ordering
Thread-Based Scoping: Agents working on the same task share context through thread IDs
Flexible Metadata Filtering: Store custom structured data with any JSON-serializable fields and filter using 16 powerful operators
Date Range Filtering: Filter context entries by creation timestamp using ISO 8601 format
Tag-Based Organization: Efficient context retrieval with normalized, indexed tags
Summary Generation: Optional automatic LLM-based summarization returned alongside truncated text_content in all search tool results for better agent context efficiency (enabled by default with Ollama)
Full-Text Search: Linguistic search with stemming, ranking, boolean queries (FTS5/tsvector), and cross-encoder reranking. Auto-enabled by default (ENABLE_FTS=auto); needs no extra dependencies
Semantic Search: Vector similarity search for meaning-based retrieval with cross-encoder reranking. Auto-enabled by default (ENABLESEMANTICSEARCH=auto) whenever an embedding provider is available (embedding generation is on by default)
Hybrid Search: Combined FTS + semantic search using Reciprocal Rank Fusion (RRF) with cross-encoder reranking. Auto-enabled by default (ENABLEHYBRIDSEARCH=auto) whenever at least one of full-text or semantic search is available
Server-Side Grep: Literal/regex, line-oriented, unranked pattern matching over stored records (grepcontext) — the precise-locate complement to full-text/semantic search, with ripgrep-style output modes and bounded results. Auto-enabled by default (ENABLEGREP_CONTEXT=auto), pure-Python so it behaves identically on SQLite and PostgreSQL
Record Navigation (indextree): navigatecontext builds an on-demand Markdown-heading table of contents per record, with the entry summary as the root node; optional per-node LLM summaries (on by default) enrich each section. Pair with readcontextrange to extract any section

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Context: common questions

Is Context MCP server safe?: Mostly: it is graded B (83/100). Read the Context safety report
How do I install Context?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Context need an API key?: Yes. The registry entry asks for POSTGRESQL_CONNECTION_STRING, POSTGRESQL_PASSWORD, ANTHROPIC_API_KEY, OPENAI_API_KEY and 5 more.
Is Context maintained?: The last commit was 37 days ago (2026-09-27). The latest release is v2.2.2.
What can I use instead of Context?: Servers from other publishers that do the same job: Memanto MCP server, Butterbase AI MCP server and World Model MCP server.
How does Context compare with other AI and agents MCP servers?: safety score 83/100 (higher than 68% of 4,460 AI and agents servers); github stars 9 (more than 83% of 2,711 AI and agents servers); downloads a week 67 (more than 53% of 1,538 AI and agents servers with a package). Full comparison.

Alternatives to Context

Same job from other publishers: the closest match first, then the best rated.

Memanto
MCP server for Memanto - persistent semantic memory for any MCP-compatible agent
not reviewed
Established
A
Butterbase AI
Butterbase MCP server — manage your backend: schemas, auth, functions, storage, RAG, deploys.
not reviewed
Established
A
World Model MCP
Persistent 3D/2D spatial world model for AI agents with dynamic velocity and entity tracking.
not reviewed
Established
A
Total Agent Memory
Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall
not reviewed
Established
A

Run it through the gateway

Local package. It runs on your machine, not through the gateway.

Rating: —
Safety grade: B · 83/100
Stars: 9
Downloads/wk: 67
Price: Free
Licence: NOASSERTION
Transport: Local · mixed
Version: 2.2.2
Category: AI and agents
Last release: 2026-09-27

Credentials it needs

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_STRINGsecretComplete PostgreSQL connection string (overrides individual settings if provided)
POSTGRESQL_HOSTPostgreSQL server host address
POSTGRESQL_PORTPostgreSQL server port number
POSTGRESQL_USERPostgreSQL database username
POSTGRESQL_PASSWORDsecretPostgreSQL 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_KEYsecretAnthropic 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_KEYsecretOpenAI API key for OpenAI embedding provider
OPENAI_API_BASECustom base URL for OpenAI-compatible APIs
OPENAI_ORGANIZATIONOpenAI organization ID
AZURE_OPENAI_API_KEYsecretAzure 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_TOKENsecretHuggingFace Hub API token for HuggingFace embedding provider
VOYAGE_API_KEYsecretVoyage 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_KEYsecretLangSmith 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_TOKENsecretBearer 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_STRINGsecretComplete PostgreSQL connection string (overrides individual settings if provided)
POSTGRESQL_HOSTPostgreSQL server host address
POSTGRESQL_PORTPostgreSQL server port number
POSTGRESQL_USERPostgreSQL database username
POSTGRESQL_PASSWORDsecretPostgreSQL 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_KEYsecretAnthropic 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_KEYsecretOpenAI API key for OpenAI embedding provider
OPENAI_API_BASECustom base URL for OpenAI-compatible APIs
OPENAI_ORGANIZATIONOpenAI organization ID
AZURE_OPENAI_API_KEYsecretAzure 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_TOKENsecretHuggingFace Hub API token for HuggingFace embedding provider
VOYAGE_API_KEYsecretVoyage 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_KEYsecretLangSmith 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_TOKENsecretBearer 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.

Own this server?

Claim it to keep the listing current and reply to reviews. Claiming never changes the grade or hides a review.

Claim listing

Badge for your README

Shows the safety grade and links back to this page. It updates itself after every scan and review.

[![mcp.market](https://mcp.market/badge/alex-feel-mcp-context-server.svg)](https://mcp.market/server/alex-feel-mcp-context-server)

How the badge works