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.
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.
| Capability | Evidence | Kind |
|---|---|---|
| Context Engineering | matched context engineering | DER |
| Agent Memory | matched agent memory | DER |
| Agent Skills & Plugins | matched subagents | DER |
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
| Platform | Basis |
|---|---|
| Roo CodeDiscontinued | Roo Code documented support for MCP but is discontinued. Project shut down and repository archived. |
Unknown17
| Platform | Basis |
|---|---|
| OpenClaw | Could not confirm whether OpenClaw supports MCP. |
| OpenHands | OpenHands 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. |
| Aider | Could 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 down | Could not confirm whether Amazon Q Developer supports MCP. |
| Amazon Bedrock Agents (Agents Classic)Maintenance only | Could not confirm whether Amazon Bedrock Agents (Agents Classic) supports MCP. |
| GPTs (custom GPTs)Winding down | Could 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 ExtensionsDiscontinued | Could not confirm whether GitHub Copilot Extensions supports MCP. |
| Google AI Studio | Could not confirm whether Google AI Studio supports MCP. |
| JulesWinding down | Could not confirm whether Jules supports MCP. |
| Microsoft Copilot | Could not confirm whether Microsoft Copilot supports MCP. |
| Microsoft Copilot Studio | Microsoft 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 Agent | Replit 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 Cody | Could not confirm whether Sourcegraph Cody supports MCP. |
| v0 | v0 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.
| Registry | Package | Transport | Runtime |
|---|---|---|---|
| oci | ghcr.io/alex-feel/mcp-context-server:2.2.2 | streamable-http | docker |
| pypi | mcp-context-server | stdio | not stated |
Environment variables SRC
| Name | Required | Secret | Publisher's description |
|---|---|---|---|
| LOG_LEVEL | No | No | Log level |
| STORAGE_BACKEND | No | No | Storage backend type: sqlite (default) or postgresql |
| MAX_IMAGE_SIZE_MB | No | No | Maximum individual image size in megabytes |
| MAX_TOTAL_SIZE_MB | No | No | Maximum total request size in megabytes |
| DB_PATH | No | No | Custom database file location path |
| POOL_MAX_READERS | No | No | Maximum number of concurrent read connections in the pool |
| POOL_MAX_WRITERS | No | No | Maximum number of concurrent write connections in the pool |
| POOL_CONNECTION_TIMEOUT_S | No | No | Connection timeout in seconds |
| POOL_IDLE_TIMEOUT_S | No | No | Idle connection timeout in seconds |
| POOL_HEALTH_CHECK_INTERVAL_S | No | No | Connection health check interval in seconds |
| RETRY_MAX_RETRIES | No | No | Maximum number of retry attempts for failed operations |
| RETRY_BASE_DELAY_S | No | No | Base delay in seconds between retry attempts |
| RETRY_MAX_DELAY_S | No | No | Maximum delay in seconds between retry attempts |
| RETRY_JITTER | No | No | Enable random jitter in retry delays |
| RETRY_BACKOFF_FACTOR | No | No | Exponential backoff multiplication factor for retries |
| SQLITE_FOREIGN_KEYS | No | No | Enable SQLite foreign key constraints |
| SQLITE_JOURNAL_MODE | No | No | SQLite journal mode (e.g., WAL, DELETE) |
| SQLITE_SYNCHRONOUS | No | No | SQLite synchronous mode (e.g., NORMAL, FULL, OFF) |
| SQLITE_TEMP_STORE | No | No | SQLite temporary storage location (e.g., MEMORY, FILE) |
| SQLITE_MMAP_SIZE | No | No | SQLite memory-mapped I/O size in bytes |
| SQLITE_CACHE_SIZE | No | No | SQLite cache size (negative value for KB, positive for pages) |
| SQLITE_PAGE_SIZE | No | No | SQLite page size in bytes |
| SQLITE_WAL_AUTOCHECKPOINT | No | No | SQLite WAL autocheckpoint threshold in pages |
| SQLITE_BUSY_TIMEOUT_MS | No | No | SQLite busy timeout in milliseconds |
| SQLITE_WAL_CHECKPOINT | No | No | SQLite WAL checkpoint mode (e.g., PASSIVE, FULL, RESTART) |
| SHUTDOWN_TIMEOUT_S | No | No | Server shutdown timeout in seconds |
| SHUTDOWN_TIMEOUT_TEST_S | No | No | Test mode shutdown timeout in seconds |
| QUEUE_TIMEOUT_S | No | No | Queue operation timeout in seconds |
| QUEUE_TIMEOUT_TEST_S | No | No | Test mode queue timeout in seconds |
| CIRCUIT_BREAKER_FAILURE_THRESHOLD | No | No | Circuit breaker failure threshold before opening |
| CIRCUIT_BREAKER_RECOVERY_TIMEOUT_S | No | No | Circuit breaker recovery timeout in seconds |
| CIRCUIT_BREAKER_HALF_OPEN_MAX_CALLS | No | No | Maximum calls allowed in circuit breaker half-open state |
| POSTGRESQL_CONNECTION_STRING | No | Secret | Complete PostgreSQL connection string (overrides individual settings if provided) |
| POSTGRESQL_HOST | No | No | PostgreSQL server host address |
| POSTGRESQL_PORT | No | No | PostgreSQL server port number |
| POSTGRESQL_USER | No | No | PostgreSQL database username |
| POSTGRESQL_PASSWORD | No | Secret | PostgreSQL database password |
| POSTGRESQL_DATABASE | No | No | PostgreSQL database name |
| POSTGRESQL_POOL_MIN | No | No | PostgreSQL connection pool minimum size |
| POSTGRESQL_POOL_MAX | No | No | PostgreSQL connection pool maximum size |
| POSTGRESQL_POOL_TIMEOUT_S | No | No | PostgreSQL connection pool timeout in seconds |
| POSTGRESQL_COMMAND_TIMEOUT_S | No | No | PostgreSQL command execution timeout in seconds |
| POSTGRESQL_MIGRATION_TIMEOUT_S | No | No | Timeout in seconds for PostgreSQL migration operations (default: 300) |
| POSTGRESQL_MAX_INACTIVE_LIFETIME_S | No | No | Close idle PostgreSQL connections after this many seconds (0 to disable, default: 300) |
| POSTGRESQL_MAX_QUERIES | No | No | Recycle PostgreSQL connections after this many queries (0 to disable, default: 10000) |
| POSTGRESQL_TCP_KEEPALIVES_IDLE_S | No | No | Seconds of idle time before sending first TCP keepalive probe (0 to disable, default: 15) |
| POSTGRESQL_TCP_KEEPALIVES_INTERVAL_S | No | No | Seconds between subsequent TCP keepalive probes (0 to disable, default: 5) |
| POSTGRESQL_TCP_KEEPALIVES_COUNT | No | No | Number of failed TCP keepalive probes before connection is considered dead (0 to disable, default: 3) |
| POSTGRESQL_STATEMENT_CACHE_SIZE | No | No | asyncpg prepared statement cache size. Set to 0 for external pooler compatibility (PgBouncer transaction mode, Pgpool-II, etc.). Default: 100 |
| POSTGRESQL_MAX_CACHED_STATEMENT_LIFETIME_S | No | No | Maximum lifetime of cached prepared statements in seconds (default: 300). Has no effect when statement_cache_size=0 |
| POSTGRESQL_MAX_CACHEABLE_STATEMENT_SIZE | No | No | Maximum size of statement to cache in bytes (default: 15360). Has no effect when statement_cache_size=0 |
| POSTGRESQL_SSL_MODE | No | No | PostgreSQL SSL mode (disable, allow, prefer, require, verify-ca, verify-full) |
| POSTGRESQL_SCHEMA | No | No | PostgreSQL schema name for table and index operations (default: public) |
| ENABLE_SEMANTIC_SEARCH | No | No | Enable semantic search functionality |
| ENABLE_EMBEDDING_GENERATION | No | No | Enable embedding generation for stored context. Default true - server fails if dependencies not met. Set false to disable embeddings. |
| OLLAMA_HOST | No | No | Ollama API host URL for embedding generation |
| OLLAMA_AUTO_PULL | No | No | Automatically pull missing Ollama models on startup (default: true) |
| OLLAMA_PULL_TIMEOUT_S | No | No | Timeout in seconds for pulling Ollama models (default: 900, range: 30-3600) |
| EMBEDDING_OLLAMA_TRUNCATE | No | No | Ollama embedding truncation mode: false (default) returns error when context exceeded, true enables silent truncation |
| EMBEDDING_OLLAMA_NUM_CTX | No | No | Ollama embedding context window size in tokens (default: 4096, range: 512-2097152) |
| EMBEDDING_MODEL | No | No | Embedding model name for semantic search |
| EMBEDDING_DIM | No | No | Embedding vector dimensions |
| EMBEDDING_TIMEOUT_S | No | No | Timeout in seconds for embedding generation API calls |
| EMBEDDING_RETRY_MAX_ATTEMPTS | No | No | Maximum number of retry attempts for embedding generation |
| EMBEDDING_RETRY_BASE_DELAY_S | No | No | Base delay in seconds between retry attempts (with exponential backoff) |
| EMBEDDING_MAX_CONCURRENT | No | No | Maximum concurrent embedding generation operations (default: 3, range: 1-20) |
| ENABLE_SUMMARY_GENERATION | No | No | Enable summary generation for stored context. Default true - server fails if dependencies not met. Set false to disable summaries. |
| SUMMARY_PROVIDER | No | No | Summary provider: ollama (default), openai, or anthropic |
| SUMMARY_MODEL | No | No | Summary generation model name (default: qwen3:0.6b) |
| SUMMARY_MAX_TOKENS | No | No | Maximum output tokens for summary generation (default: 4000, range: 50-16384). Increase if summaries are truncated by reasoning models |
| SUMMARY_TIMEOUT_S | No | No | Timeout in seconds for summary generation API calls |
| SUMMARY_RETRY_MAX_ATTEMPTS | No | No | Maximum number of retry attempts for summary generation |
| SUMMARY_RETRY_BASE_DELAY_S | No | No | Base delay in seconds between retry attempts (with exponential backoff) |
| SUMMARY_MAX_CONCURRENT | No | No | Maximum concurrent summary generation operations (default: 3, range: 1-20) |
| SUMMARY_PROMPT | No | No | Custom summarization prompt. Overrides the built-in default. Used as system message for the LLM. |
| SUMMARY_MIN_CONTENT_LENGTH | No | No | Minimum text content length in characters to trigger summary generation (default: 500, range: 0-10000). Set to 0 to always generate. |
| SUMMARY_OLLAMA_NUM_CTX | No | No | Ollama summary context window size in tokens (default: 32768, range: 512-2097152) |
| SUMMARY_OLLAMA_TRUNCATE | No | No | Ollama summary truncation mode: false (default) returns error when context exceeded, true enables silent truncation |
| SUMMARY_OPENAI_REASONING_EFFORT | No | No | Reasoning 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_EFFORT | No | No | Effort level for Anthropic Claude models (default: none). Valid values: max, high, medium, low. Controls inference effort (adaptive thinking) |
| ANTHROPIC_API_KEY | No | Secret | Anthropic API key for summary generation |
| ENABLE_FTS | No | No | Enable full-text search functionality |
| FTS_LANGUAGE | No | No | Language for FTS stemming (e.g., english, german, french) |
| FTS_RERANK_WINDOW_SIZE | No | No | Characters of context around each FTS match for reranking passage extraction (default: 750) |
| FTS_RERANK_GAP_MERGE | No | No | Merge FTS match regions within this character distance (default: 100) |
| ENABLE_HYBRID_SEARCH | No | No | Enable hybrid search combining FTS and semantic search with RRF fusion |
| HYBRID_RRF_K | No | No | RRF smoothing constant for hybrid search (default 60) |
| HYBRID_RRF_OVERFETCH | No | No | Multiplier for over-fetching results before RRF fusion (default: 2) |
| HYBRID_FTS_OR_THRESHOLD | No | No | Minimum significant query terms to switch hybrid FTS from AND to OR logic (default: 4) |
| SEARCH_DEFAULT_SORT_BY | No | No | Default sort order for search results: relevance (only 'relevance' supported in current version) |
| SEARCH_TRUNCATION_LENGTH | No | No | Maximum character length for truncated text_content in search results (default: 300, range: 50-1000) |
| ENABLE_CHUNKING | No | No | Enable text chunking for embedding generation (default: true) |
| CHUNK_SIZE | No | No | Target chunk size in characters (default: 1500) |
| CHUNK_OVERLAP | No | No | Overlap between chunks in characters (default: 150) |
| CHUNK_AGGREGATION | No | No | Chunk score aggregation method: max (only 'max' supported in current version) |
| CHUNK_DEDUP_OVERFETCH | No | No | Multiplier for over-fetching chunks before deduplication (default: 5) |
| ENABLE_RERANKING | No | No | Enable cross-encoder reranking of search results (default: true) |
| RERANKING_PROVIDER | No | No | Reranking provider (default: flashrank) |
| RERANKING_MODEL | No | No | Reranking model name (default: ms-marco-MiniLM-L-12-v2) |
| RERANKING_MAX_LENGTH | No | No | Maximum input length for reranking in tokens (default: 512) |
| RERANKING_OVERFETCH | No | No | Multiplier for over-fetching results before reranking (default: 4) |
| RERANKING_CACHE_DIR | No | No | Directory for caching reranking models |
| RERANKING_CHARS_PER_TOKEN | No | No | Estimated characters per token for passage size validation (default: 4.0, range: 2.0-8.0) |
| RERANKING_INTRA_OP_THREADS | No | No | ONNX Runtime intra-operation parallelism threads for reranking (default: 0 = auto-detect) |
| RERANKING_CPU_MEM_ARENA | No | No | Enable ONNX Runtime CPU memory arena for reranking (default: false) |
| RERANKING_BATCH_SIZE | No | No | Maximum passages per ONNX Runtime inference batch during reranking (default: 32) |
| EMBEDDING_PROVIDER | No | No | Embedding provider: ollama (default), openai, azure, huggingface, or voyage |
| OPENAI_API_KEY | No | Secret | OpenAI API key for OpenAI embedding provider |
| OPENAI_API_BASE | No | No | Custom base URL for OpenAI-compatible APIs |
| OPENAI_ORGANIZATION | No | No | OpenAI organization ID |
| AZURE_OPENAI_API_KEY | No | Secret | Azure OpenAI API key |
| AZURE_OPENAI_ENDPOINT | No | No | Azure OpenAI endpoint URL |
| AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME | No | No | Azure OpenAI embedding deployment name |
| AZURE_OPENAI_API_VERSION | No | No | Azure OpenAI API version (default: 2024-02-01) |
| HUGGINGFACEHUB_API_TOKEN | No | Secret | HuggingFace Hub API token for HuggingFace embedding provider |
| VOYAGE_API_KEY | No | Secret | Voyage AI API key for Voyage embedding provider |
| VOYAGE_TRUNCATION | No | No | Voyage AI truncation mode: false (default) returns error when context exceeded, true enables silent truncation |
| VOYAGE_BATCH_SIZE | No | No | Voyage AI batch size for embedding requests |
| LANGSMITH_TRACING | No | No | Enable LangSmith tracing |
| LANGSMITH_API_KEY | No | Secret | LangSmith API key |
| LANGSMITH_PROJECT | No | No | LangSmith project name |
| LANGSMITH_ENDPOINT | No | No | LangSmith API endpoint URL |
| METADATA_INDEXED_FIELDS | No | No | Comma-separated list of metadata fields to index (field:type format) |
| METADATA_INDEX_SYNC_MODE | No | No | Index sync mode: strict (fail), auto (sync), warn (log), additive (default, add missing only) |
| MCP_TRANSPORT | No | No | Transport mode: stdio for local, http for Docker/remote |
| FASTMCP_HOST | No | No | HTTP bind address (use 0.0.0.0 for Docker) |
| FASTMCP_PORT | No | No | HTTP port number |
| FASTMCP_STATELESS_HTTP | No | No | Enable 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_TOOLS | No | No | Comma-separated list of tools to disable (e.g., delete_context,update_context) |
| MCP_AUTH_TOKEN | No | Secret | Bearer token for HTTP authentication (required when using SimpleTokenVerifier) |
| MCP_AUTH_CLIENT_ID | No | No | Client ID to assign to authenticated requests |
| MCP_AUTH_PROVIDER | No | No | Authentication provider: none (default), simple_token |
| MCP_SERVER_INSTRUCTIONS | No | No | Custom 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.
| Signal | Evidence | How observed | Observed |
|---|---|---|---|
| Runs a local process | runs locally via pypi | registry metadata | 2026-11-21 |
| Asks for a secret | declares secret env var(s): POSTGRESQL_CONNECTION_STRING, POSTGRESQL_PASSWORD, ANTHROPIC_API_KEY, OPENAI_API_KEY, AZURE_OPENAI_API_KEY | registry 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.
Version history SRC
- 2.2.2
- 2.2.1
- 2.2.0
- 2.1.0
- 2.0.0
- 1.7.1
- 1.7.0
- 1.6.0
32 earlier versions
- 1.5.0
- 1.4.0
- 1.3.3
- 1.3.2
- 1.3.1
- 1.3.0
- 1.2.1
- 1.2.0
- 1.1.0
- 1.0.0
- 0.17.0
- 0.16.1
- 0.16.0
- 0.15.1
- 0.15.0
- 0.14.1
- 0.14.0
- 0.13.0
- 0.12.0
- 0.11.0
- 0.10.0
- 0.9.0
- 0.8.0
- 0.7.0
- 0.6.0
- 0.5.1
- 0.5.0
- 0.4.1
- 0.4.0
- 0.3.0
- 0.2.0
- 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.
- First seen
Competitors and alternativesDER
Paired by shared capabilities and integrations. Similar on paper; not tested side by side.
Direct
Same type, overlapping capabilities.
MCP serverby NickCirvSRC
SharesAgent Skills & PluginsContext EngineeringAgent Memory
MCP serverby vshulczSRC
SharesAgent Skills & PluginsAgent Memory
MCP serverby mksgluHEU
SharesAgent Skills & PluginsContext Engineering
Adjacent
A different form or a partial overlap.
Pluginby davegoldblattHEU
SharesAgent Skills & PluginsContext EngineeringAgent Memory
Infrastructureby kayba-aiHEU
SharesContext EngineeringAgent Memory
Infrastructureby omdsh-devHEU
SharesContext EngineeringAgent Memory
Infrastructureby mindmuxaiHEU
SharesContext EngineeringAgent Memory
Provenance
Which source set each field, what kind of claim it is, and when.
| Field | Source | Kind | Set on |
|---|---|---|---|
| Canonical URL | Official MCP Registry | SRC | 2026-11-21 |
| Publisher | Official MCP Registry | SRC | 2026-11-21 |
| Description | Official MCP Registry | SRC | 2026-11-21 |
| Hosting | Official MCP Registry | SRC | 2026-11-21 |
| Integration type | Official MCP Registry | SRC | 2026-11-21 |
| Languages | GitHub repository metadata | SRC | 2026-11-21 |
| Latest version | Official MCP Registry | SRC | 2026-11-21 |
| Name | Official MCP Registry | SRC | 2026-11-21 |
| Type | Official MCP Registry | SRC | 2026-11-21 |
| Published | Official MCP Registry | SRC | 2026-11-21 |
| Repository | Official MCP Registry | SRC | 2026-11-21 |
| source_updated_at | Official MCP Registry | SRC | 2026-11-21 |
| Source URL | Official MCP Registry | SRC | 2026-11-21 |
Sources
- Official MCP Registry: registry.modelcontextprotocol.io (external)checked
Not verified by a researcher. Last seen in a source on . Report incorrect information