AgentSidekick

mcp-context-server

MCP serverby alex-feelSRC

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

SRC Publisher-stated: these are the publisher's own words, not an assessment.

RepositorySource listing

Key facts

Type
MCP server · mcp-localSRC
Publisher
alex-feel · organizationSRC
Licence
Unknown
Open source
Unknown
Hosting
Local (runs on your machine)SRC
Latest version
2.2.2SRC
Languages
pythonSRC
First published
SRC
In this catalogue since
DER
Last verified
Not verified by a researcher. Last seen in a source on 2026-11-21.

Capabilities and categories

Assigned by keyword rules from the description unless marked otherwise. The matched word is shown so you can judge the match.

CapabilityEvidenceKind
Context Engineeringmatched context engineeringDER
Agent Memorymatched agent memoryDER
Agent Skills & Pluginsmatched subagentsDER

Filed underAgent InfrastructureDeveloper ToolsAI Coding AgentsAgent Runtime & DeploymentCoding Agent CLIs & ExtensionsMemory & State

Integrations DER

No third-party service is named in the description or package metadata.

Platform compatibility

No pairing has been tested by AgentSidekick. Each status says what kind of evidence exists, not whether it works for you.

Protocol-level29

Each platform listed officially documents support for MCP. This specific pairing has not been tested.

Platform discontinued1
PlatformBasis
Roo CodeDiscontinuedRoo Code documented support for MCP but is discontinued. Project shut down and repository archived.
Unknown17
PlatformBasis
OpenClawCould not confirm whether OpenClaw supports MCP.
OpenHandsOpenHands documents MCP support, but it runs only on web, api, slack surfaces and this server runs locally as a process on your machine. Whether OpenHands can reach a local server is not established.
AiderCould not confirm whether Aider supports MCP.
Bolt (bolt.new)Bolt (bolt.new) documents MCP support, but it runs only on web surfaces and this server runs locally as a process on your machine. Whether Bolt (bolt.new) can reach a local server is not established.
Amazon Q DeveloperWinding downCould not confirm whether Amazon Q Developer supports MCP.
Amazon Bedrock Agents (Agents Classic)Maintenance onlyCould not confirm whether Amazon Bedrock Agents (Agents Classic) supports MCP.
GPTs (custom GPTs)Winding downCould not confirm whether GPTs (custom GPTs) supports MCP.
Gemini (app)Gemini (app) documents MCP support, but it runs only on web, mobile surfaces and this server runs locally as a process on your machine. Whether Gemini (app) can reach a local server is not established.
Gemini Enterprise Agent Platform (formerly Vertex AI / Vertex AI Agent Builder)Gemini Enterprise Agent Platform (formerly Vertex AI / Vertex AI Agent Builder) documents MCP support, but it runs only on web, api surfaces and this server runs locally as a process on your machine. Whether Gemini Enterprise Agent Platform (formerly Vertex AI / Vertex AI Agent Builder) can reach a local server is not established.
GitHub Copilot ExtensionsDiscontinuedCould not confirm whether GitHub Copilot Extensions supports MCP.
Google AI StudioCould not confirm whether Google AI Studio supports MCP.
JulesWinding downCould not confirm whether Jules supports MCP.
Microsoft CopilotCould not confirm whether Microsoft Copilot supports MCP.
Microsoft Copilot StudioMicrosoft Copilot Studio documents MCP support, but it runs only on web surfaces and this server runs locally as a process on your machine. Whether Microsoft Copilot Studio can reach a local server is not established.
Replit AgentReplit Agent documents MCP support, but it runs only on web surfaces and this server runs locally as a process on your machine. Whether Replit Agent can reach a local server is not established.
Sourcegraph CodyCould not confirm whether Sourcegraph Cody supports MCP.
v0v0 documents MCP support, but it runs only on web, api surfaces and this server runs locally as a process on your machine. Whether v0 can reach a local server is not established.

Install

Read from registry metadata. Follow the publisher's instructions; we have not run this.

Packages
RegistryPackageTransportRuntime
ocighcr.io/alex-feel/mcp-context-server:2.2.2streamable-httpdocker
pypimcp-context-serverstdionot stated

Environment variables SRC

NameRequiredSecretPublisher's description
LOG_LEVELNoNoLog level
STORAGE_BACKENDNoNoStorage backend type: sqlite (default) or postgresql
MAX_IMAGE_SIZE_MBNoNoMaximum individual image size in megabytes
MAX_TOTAL_SIZE_MBNoNoMaximum total request size in megabytes
DB_PATHNoNoCustom database file location path
POOL_MAX_READERSNoNoMaximum number of concurrent read connections in the pool
POOL_MAX_WRITERSNoNoMaximum number of concurrent write connections in the pool
POOL_CONNECTION_TIMEOUT_SNoNoConnection timeout in seconds
POOL_IDLE_TIMEOUT_SNoNoIdle connection timeout in seconds
POOL_HEALTH_CHECK_INTERVAL_SNoNoConnection health check interval in seconds
RETRY_MAX_RETRIESNoNoMaximum number of retry attempts for failed operations
RETRY_BASE_DELAY_SNoNoBase delay in seconds between retry attempts
RETRY_MAX_DELAY_SNoNoMaximum delay in seconds between retry attempts
RETRY_JITTERNoNoEnable random jitter in retry delays
RETRY_BACKOFF_FACTORNoNoExponential backoff multiplication factor for retries
SQLITE_FOREIGN_KEYSNoNoEnable SQLite foreign key constraints
SQLITE_JOURNAL_MODENoNoSQLite journal mode (e.g., WAL, DELETE)
SQLITE_SYNCHRONOUSNoNoSQLite synchronous mode (e.g., NORMAL, FULL, OFF)
SQLITE_TEMP_STORENoNoSQLite temporary storage location (e.g., MEMORY, FILE)
SQLITE_MMAP_SIZENoNoSQLite memory-mapped I/O size in bytes
SQLITE_CACHE_SIZENoNoSQLite cache size (negative value for KB, positive for pages)
SQLITE_PAGE_SIZENoNoSQLite page size in bytes
SQLITE_WAL_AUTOCHECKPOINTNoNoSQLite WAL autocheckpoint threshold in pages
SQLITE_BUSY_TIMEOUT_MSNoNoSQLite busy timeout in milliseconds
SQLITE_WAL_CHECKPOINTNoNoSQLite WAL checkpoint mode (e.g., PASSIVE, FULL, RESTART)
SHUTDOWN_TIMEOUT_SNoNoServer shutdown timeout in seconds
SHUTDOWN_TIMEOUT_TEST_SNoNoTest mode shutdown timeout in seconds
QUEUE_TIMEOUT_SNoNoQueue operation timeout in seconds
QUEUE_TIMEOUT_TEST_SNoNoTest mode queue timeout in seconds
CIRCUIT_BREAKER_FAILURE_THRESHOLDNoNoCircuit breaker failure threshold before opening
CIRCUIT_BREAKER_RECOVERY_TIMEOUT_SNoNoCircuit breaker recovery timeout in seconds
CIRCUIT_BREAKER_HALF_OPEN_MAX_CALLSNoNoMaximum calls allowed in circuit breaker half-open state
POSTGRESQL_CONNECTION_STRINGNoSecretComplete PostgreSQL connection string (overrides individual settings if provided)
POSTGRESQL_HOSTNoNoPostgreSQL server host address
POSTGRESQL_PORTNoNoPostgreSQL server port number
POSTGRESQL_USERNoNoPostgreSQL database username
POSTGRESQL_PASSWORDNoSecretPostgreSQL database password
POSTGRESQL_DATABASENoNoPostgreSQL database name
POSTGRESQL_POOL_MINNoNoPostgreSQL connection pool minimum size
POSTGRESQL_POOL_MAXNoNoPostgreSQL connection pool maximum size
POSTGRESQL_POOL_TIMEOUT_SNoNoPostgreSQL connection pool timeout in seconds
POSTGRESQL_COMMAND_TIMEOUT_SNoNoPostgreSQL command execution timeout in seconds
POSTGRESQL_MIGRATION_TIMEOUT_SNoNoTimeout in seconds for PostgreSQL migration operations (default: 300)
POSTGRESQL_MAX_INACTIVE_LIFETIME_SNoNoClose idle PostgreSQL connections after this many seconds (0 to disable, default: 300)
POSTGRESQL_MAX_QUERIESNoNoRecycle PostgreSQL connections after this many queries (0 to disable, default: 10000)
POSTGRESQL_TCP_KEEPALIVES_IDLE_SNoNoSeconds of idle time before sending first TCP keepalive probe (0 to disable, default: 15)
POSTGRESQL_TCP_KEEPALIVES_INTERVAL_SNoNoSeconds between subsequent TCP keepalive probes (0 to disable, default: 5)
POSTGRESQL_TCP_KEEPALIVES_COUNTNoNoNumber of failed TCP keepalive probes before connection is considered dead (0 to disable, default: 3)
POSTGRESQL_STATEMENT_CACHE_SIZENoNoasyncpg prepared statement cache size. Set to 0 for external pooler compatibility (PgBouncer transaction mode, Pgpool-II, etc.). Default: 100
POSTGRESQL_MAX_CACHED_STATEMENT_LIFETIME_SNoNoMaximum lifetime of cached prepared statements in seconds (default: 300). Has no effect when statement_cache_size=0
POSTGRESQL_MAX_CACHEABLE_STATEMENT_SIZENoNoMaximum size of statement to cache in bytes (default: 15360). Has no effect when statement_cache_size=0
POSTGRESQL_SSL_MODENoNoPostgreSQL SSL mode (disable, allow, prefer, require, verify-ca, verify-full)
POSTGRESQL_SCHEMANoNoPostgreSQL schema name for table and index operations (default: public)
ENABLE_SEMANTIC_SEARCHNoNoEnable semantic search functionality
ENABLE_EMBEDDING_GENERATIONNoNoEnable embedding generation for stored context. Default true - server fails if dependencies not met. Set false to disable embeddings.
OLLAMA_HOSTNoNoOllama API host URL for embedding generation
OLLAMA_AUTO_PULLNoNoAutomatically pull missing Ollama models on startup (default: true)
OLLAMA_PULL_TIMEOUT_SNoNoTimeout in seconds for pulling Ollama models (default: 900, range: 30-3600)
EMBEDDING_OLLAMA_TRUNCATENoNoOllama embedding truncation mode: false (default) returns error when context exceeded, true enables silent truncation
EMBEDDING_OLLAMA_NUM_CTXNoNoOllama embedding context window size in tokens (default: 4096, range: 512-2097152)
EMBEDDING_MODELNoNoEmbedding model name for semantic search
EMBEDDING_DIMNoNoEmbedding vector dimensions
EMBEDDING_TIMEOUT_SNoNoTimeout in seconds for embedding generation API calls
EMBEDDING_RETRY_MAX_ATTEMPTSNoNoMaximum number of retry attempts for embedding generation
EMBEDDING_RETRY_BASE_DELAY_SNoNoBase delay in seconds between retry attempts (with exponential backoff)
EMBEDDING_MAX_CONCURRENTNoNoMaximum concurrent embedding generation operations (default: 3, range: 1-20)
ENABLE_SUMMARY_GENERATIONNoNoEnable summary generation for stored context. Default true - server fails if dependencies not met. Set false to disable summaries.
SUMMARY_PROVIDERNoNoSummary provider: ollama (default), openai, or anthropic
SUMMARY_MODELNoNoSummary generation model name (default: qwen3:0.6b)
SUMMARY_MAX_TOKENSNoNoMaximum output tokens for summary generation (default: 4000, range: 50-16384). Increase if summaries are truncated by reasoning models
SUMMARY_TIMEOUT_SNoNoTimeout in seconds for summary generation API calls
SUMMARY_RETRY_MAX_ATTEMPTSNoNoMaximum number of retry attempts for summary generation
SUMMARY_RETRY_BASE_DELAY_SNoNoBase delay in seconds between retry attempts (with exponential backoff)
SUMMARY_MAX_CONCURRENTNoNoMaximum concurrent summary generation operations (default: 3, range: 1-20)
SUMMARY_PROMPTNoNoCustom summarization prompt. Overrides the built-in default. Used as system message for the LLM.
SUMMARY_MIN_CONTENT_LENGTHNoNoMinimum text content length in characters to trigger summary generation (default: 500, range: 0-10000). Set to 0 to always generate.
SUMMARY_OLLAMA_NUM_CTXNoNoOllama summary context window size in tokens (default: 32768, range: 512-2097152)
SUMMARY_OLLAMA_TRUNCATENoNoOllama summary truncation mode: false (default) returns error when context exceeded, true enables silent truncation
SUMMARY_OPENAI_REASONING_EFFORTNoNoReasoning 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_EFFORTNoNoEffort level for Anthropic Claude models (default: none). Valid values: max, high, medium, low. Controls inference effort (adaptive thinking)
ANTHROPIC_API_KEYNoSecretAnthropic API key for summary generation
ENABLE_FTSNoNoEnable full-text search functionality
FTS_LANGUAGENoNoLanguage for FTS stemming (e.g., english, german, french)
FTS_RERANK_WINDOW_SIZENoNoCharacters of context around each FTS match for reranking passage extraction (default: 750)
FTS_RERANK_GAP_MERGENoNoMerge FTS match regions within this character distance (default: 100)
ENABLE_HYBRID_SEARCHNoNoEnable hybrid search combining FTS and semantic search with RRF fusion
HYBRID_RRF_KNoNoRRF smoothing constant for hybrid search (default 60)
HYBRID_RRF_OVERFETCHNoNoMultiplier for over-fetching results before RRF fusion (default: 2)
HYBRID_FTS_OR_THRESHOLDNoNoMinimum significant query terms to switch hybrid FTS from AND to OR logic (default: 4)
SEARCH_DEFAULT_SORT_BYNoNoDefault sort order for search results: relevance (only 'relevance' supported in current version)
SEARCH_TRUNCATION_LENGTHNoNoMaximum character length for truncated text_content in search results (default: 300, range: 50-1000)
ENABLE_CHUNKINGNoNoEnable text chunking for embedding generation (default: true)
CHUNK_SIZENoNoTarget chunk size in characters (default: 1500)
CHUNK_OVERLAPNoNoOverlap between chunks in characters (default: 150)
CHUNK_AGGREGATIONNoNoChunk score aggregation method: max (only 'max' supported in current version)
CHUNK_DEDUP_OVERFETCHNoNoMultiplier for over-fetching chunks before deduplication (default: 5)
ENABLE_RERANKINGNoNoEnable cross-encoder reranking of search results (default: true)
RERANKING_PROVIDERNoNoReranking provider (default: flashrank)
RERANKING_MODELNoNoReranking model name (default: ms-marco-MiniLM-L-12-v2)
RERANKING_MAX_LENGTHNoNoMaximum input length for reranking in tokens (default: 512)
RERANKING_OVERFETCHNoNoMultiplier for over-fetching results before reranking (default: 4)
RERANKING_CACHE_DIRNoNoDirectory for caching reranking models
RERANKING_CHARS_PER_TOKENNoNoEstimated characters per token for passage size validation (default: 4.0, range: 2.0-8.0)
RERANKING_INTRA_OP_THREADSNoNoONNX Runtime intra-operation parallelism threads for reranking (default: 0 = auto-detect)
RERANKING_CPU_MEM_ARENANoNoEnable ONNX Runtime CPU memory arena for reranking (default: false)
RERANKING_BATCH_SIZENoNoMaximum passages per ONNX Runtime inference batch during reranking (default: 32)
EMBEDDING_PROVIDERNoNoEmbedding provider: ollama (default), openai, azure, huggingface, or voyage
OPENAI_API_KEYNoSecretOpenAI API key for OpenAI embedding provider
OPENAI_API_BASENoNoCustom base URL for OpenAI-compatible APIs
OPENAI_ORGANIZATIONNoNoOpenAI organization ID
AZURE_OPENAI_API_KEYNoSecretAzure OpenAI API key
AZURE_OPENAI_ENDPOINTNoNoAzure OpenAI endpoint URL
AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAMENoNoAzure OpenAI embedding deployment name
AZURE_OPENAI_API_VERSIONNoNoAzure OpenAI API version (default: 2024-02-01)
HUGGINGFACEHUB_API_TOKENNoSecretHuggingFace Hub API token for HuggingFace embedding provider
VOYAGE_API_KEYNoSecretVoyage AI API key for Voyage embedding provider
VOYAGE_TRUNCATIONNoNoVoyage AI truncation mode: false (default) returns error when context exceeded, true enables silent truncation
VOYAGE_BATCH_SIZENoNoVoyage AI batch size for embedding requests
LANGSMITH_TRACINGNoNoEnable LangSmith tracing
LANGSMITH_API_KEYNoSecretLangSmith API key
LANGSMITH_PROJECTNoNoLangSmith project name
LANGSMITH_ENDPOINTNoNoLangSmith API endpoint URL
METADATA_INDEXED_FIELDSNoNoComma-separated list of metadata fields to index (field:type format)
METADATA_INDEX_SYNC_MODENoNoIndex sync mode: strict (fail), auto (sync), warn (log), additive (default, add missing only)
MCP_TRANSPORTNoNoTransport mode: stdio for local, http for Docker/remote
FASTMCP_HOSTNoNoHTTP bind address (use 0.0.0.0 for Docker)
FASTMCP_PORTNoNoHTTP port number
FASTMCP_STATELESS_HTTPNoNoEnable 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_TOOLSNoNoComma-separated list of tools to disable (e.g., delete_context,update_context)
MCP_AUTH_TOKENNoSecretBearer token for HTTP authentication (required when using SimpleTokenVerifier)
MCP_AUTH_CLIENT_IDNoNoClient ID to assign to authenticated requests
MCP_AUTH_PROVIDERNoNoAuthentication provider: none (default), simple_token
MCP_SERVER_INSTRUCTIONSNoNoCustom server instructions text. Overrides built-in default. Set to empty string to disable.

Permissions and signals

Signals, not a safety verdict. They describe what the product's metadata references. Security review: not reviewed.

SignalEvidenceHow observedObserved
Runs a local processruns locally via pypiregistry metadata 2026-11-21
Asks for a secretdeclares secret env var(s): POSTGRESQL_CONNECTION_STRING, POSTGRESQL_PASSWORD, ANTHROPIC_API_KEY, OPENAI_API_KEY, AZURE_OPENAI_API_KEYregistry metadata 2026-11-21

Known advisories for the published package SRC

An advisory existing does not mean the listed version is affected: compare the vulnerable range with the version you install. None found is not evidence of safety.

No advisories found

No published advisory matches a package this product declares. Products without a declared package cannot be matched at all. This is not evidence of safety.

Evaluation

Separate dimensions, each with its evidence. There is no overall score: the dimensions do not add up to one number honestly.

Source authority

Publisher-submitted

Published to the official MCP Registry by the namespace owner. Field values are the publisher's own claims.

Publisher verification

Namespace verified by registry

The MCP Registry verifies namespace ownership (GitHub login or DNS) before publishing. This confirms who published it, not what it does.

Maintenance activity

Active

Last push 2026-11-15 (6 days before this page was built).

Licence clarity

No licence detected

GitHub did not detect a standard licence file. Without one, default copyright applies.

Installation clarity

Machine-readable

2 package(s) and 0 remote endpoint(s) declared in registry metadata.

Documentation

Repository / website only

No dedicated documentation URL on record. AgentSidekick has not assessed documentation quality.

Compatibility evidence

Protocol-level only

Compatibility is inferred from the standard it implements. No pairing has been tested.

Security review

Not reviewed

AgentSidekick has not audited this product. 2 automated signal(s) are listed under Permissions & signals — they describe what it references, not whether it is safe.

Pricing

Not published in any source we track.

Repository activity

alex-feel/mcp-context-server. Read from the GitHub API on 2026-11-21.

10SRCGitHub stars
6SRCForks
0SRCOpen issues
6d agoSRCLast push2026-11-15
v2.2.2SRCLatest release2026-03-28

Version history SRC

  1. 2.2.2
  2. 2.2.1
  3. 2.2.0
  4. 2.1.0
  5. 2.0.0
  6. 1.7.1
  7. 1.7.0
  8. 1.6.0
32 earlier versions
  1. 1.5.0
  2. 1.4.0
  3. 1.3.3
  4. 1.3.2
  5. 1.3.1
  6. 1.3.0
  7. 1.2.1
  8. 1.2.0
  9. 1.1.0
  10. 1.0.0
  11. 0.17.0
  12. 0.16.1
  13. 0.16.0
  14. 0.15.1
  15. 0.15.0
  16. 0.14.1
  17. 0.14.0
  18. 0.13.0
  19. 0.12.0
  20. 0.11.0
  21. 0.10.0
  22. 0.9.0
  23. 0.8.0
  24. 0.7.0
  25. 0.6.0
  26. 0.5.1
  27. 0.5.0
  28. 0.4.1
  29. 0.4.0
  30. 0.3.0
  31. 0.2.0
  32. 0.1.0

Change history

What changed between two ingests of the same source, and when the product was first seen. Registry releases are under Version history.

  1. First seen

Competitors and alternativesDER

Paired by shared capabilities and integrations. Similar on paper; not tested side by side.

Direct

Same type, overlapping capabilities.

engram

MCP serverby NickCirvSRC

143 GitHub starspushed 1mo agoApache-2.0

SharesAgent Skills & PluginsContext EngineeringAgent Memory

ditto

MCP serverby ohad6kSRC

306 GitHub starspushed 1mo agoMIT

SharesContext EngineeringAgent Memory

emulo

MCP serverby ohad6kSRC

306 GitHub starspushed 1mo agoMIT

SharesContext EngineeringAgent Memory

SharesAgent Skills & PluginsAgent Memory

deja-vu

MCP serverby vshulczSRC

1.6k GitHub starspushed todayMIT

SharesAgent Skills & PluginsAgent Memory

context-mode

MCP serverby mksgluHEU

34k GitHub starspushed todaylicence unknown

SharesAgent Skills & PluginsContext Engineering

Adjacent

A different form or a partial overlap.

total-recall

Pluginby davegoldblattHEU

203 GitHub starspushed 9mo agolicence unknown

SharesAgent Skills & PluginsContext EngineeringAgent Memory

agentic-context-engine

Infrastructureby kayba-aiHEU

2.6k GitHub starspushed 1mo agoApache-2.0

SharesContext EngineeringAgent Memory

SharesContext EngineeringAgent Memory

brain.md

Infrastructureby mindmuxaiHEU

723 GitHub starspushed 8d agoApache-2.0

SharesContext EngineeringAgent Memory

Provenance

Which source set each field, what kind of claim it is, and when.

FieldSourceKindSet on
Canonical URLOfficial MCP RegistrySRC2026-11-21
PublisherOfficial MCP RegistrySRC2026-11-21
DescriptionOfficial MCP RegistrySRC2026-11-21
HostingOfficial MCP RegistrySRC2026-11-21
Integration typeOfficial MCP RegistrySRC2026-11-21
LanguagesGitHub repository metadataSRC2026-11-21
Latest versionOfficial MCP RegistrySRC2026-11-21
NameOfficial MCP RegistrySRC2026-11-21
TypeOfficial MCP RegistrySRC2026-11-21
PublishedOfficial MCP RegistrySRC2026-11-21
RepositoryOfficial MCP RegistrySRC2026-11-21
source_updated_atOfficial MCP RegistrySRC2026-11-21
Source URLOfficial MCP RegistrySRC2026-11-21

Sources

Not verified by a researcher. Last seen in a source on . Report incorrect information

Page data last updated .