Boomi MCP Server
by RenEra-ai
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MONGODB_URI | Yes | MongoDB Atlas connection string for OAuth state | |
| OIDC_BASE_URL | Yes | Base URL for OAuth flow (e.g., https://boomi.renera.ai) | |
| GCP_PROJECT_ID | Yes | GCP project ID for Secret Manager (e.g., boomimcp) | |
| OIDC_CLIENT_ID | Yes | Google OAuth client ID | |
| SESSION_SECRET | Yes | Session signing key for web UI | |
| JWT_SIGNING_KEY | Yes | Stable key for signing MCP JWT tokens | |
| SECRETS_BACKEND | Yes | Backend for secrets storage (e.g., gcp) | gcp |
| BOOMI_DOCS_DB_PATH | No | Path to knowledge base database (e.g., /app/kb/boomi_knowledge_db) | |
| BOOMI_DOCS_ENABLED | No | Set to true to register KB tools and resource | false |
| OIDC_CLIENT_SECRET | Yes | Google OAuth client secret | |
| BOOMI_RT_GRACE_SHARED | No | Backs refresh-token grace cache with MongoDB (default true) | true |
| BOOMI_RT_PATCH_STRICT | No | Raise on FastMCP-contract incompatibility (default true in production) | |
| BOOMI_TOKEN_CACHE_SWR | No | Opt-in stale-while-revalidate (default false) | |
| BOOMI_DOCS_RELEASE_TAG | No | Operational marker for KB release tag | |
| BOOMI_RT_GRACE_SECONDS | No | Window during which a just-rotated refresh token still returns the same new tokens (default 60) | 60 |
| STORAGE_ENCRYPTION_KEY | Yes | Fernet key(s) for encrypting OAuth tokens at rest. Single value or comma-separated list (newest first) to enable zero-downtime key rotation via MultiFernet. | |
| BOOMI_MCP_JSON_RESPONSE | No | Enables JSON response instead of SSE-on-POST (pinned true in production) | true |
| BOOMI_RT_GRACE_MAX_SIZE | No | LRU capacity for the grace cache (default 512) | 512 |
| BOOMI_MCP_STATELESS_HTTP | No | Enables stateless MCP HTTP transport (pinned true in production) | true |
| BOOMI_RT_RECOVERY_ENABLED | No | Durable recovery of stale refresh JWTs (default true) | true |
| BOOMI_TOKEN_CACHE_DISABLE | No | Disable token cache (default off) | |
| BOOMI_RT_RECOVERY_MAX_HOPS | No | Max alias-chain depth (default 64) | 64 |
| BOOMI_TOKEN_CACHE_MAX_SIZE | No | LRU capacity (default 256) | 256 |
| BOOMI_RT_GRACE_LOCK_POLL_MS | No | Follower poll interval for distributed lock (default 100) | 100 |
| BOOMI_AUTH_PROTECTION_STRICT | No | Fail startup if shared-grace or durable-recovery cannot initialize (default true in production) | |
| BOOMI_RT_RECOVERY_COLLECTION | No | MongoDB collection for recovery (default mcp-rt-recovery) | mcp-rt-recovery |
| BOOMI_TOKEN_CACHE_SWR_WINDOW | No | Seconds before expiry at which SWR serves stale + refreshes (default 30) | 30 |
| BOOMI_TOKEN_CACHE_TTL_SECONDS | No | Upper bound on per-entry TTL (default 300) | 300 |
| BOOMI_AUTH_HEAL_CORRUPT_CLIENTS | No | Delete corrupted MongoDB docs on InvalidToken/ValidationError (default true) | true |
| BOOMI_OAUTH_DIAGNOSTICS_DISABLE | No | Set true to silence OAuth diagnostic log patches | |
| BOOMI_RT_GRACE_DISTRIBUTED_LOCK | No | Opt-in cross-instance singleflight (default false) | |
| BOOMI_RT_GRACE_LOCK_TTL_SECONDS | No | Auto-release safety bound for distributed lock (default 30) | 30 |
| BOOMI_RT_SLIDING_REFRESH_EXPIRY | No | Stamp refresh tokens with fresh sliding window when upstream omits refresh_expires_in (default true) | true |
| BOOMI_RT_GRACE_SHARED_COLLECTION | No | MongoDB collection name for shared grace cache (default mcp-rt-grace) | mcp-rt-grace |
| BOOMI_RT_RECOVERY_MAX_AGE_SECONDS | No | Maximum durable alias lifetime (default 2592000, 30 days) | 2592000 |
| BOOMI_RT_REFRESH_JWT_LEEWAY_SECONDS | No | Clock-skew tolerance on refresh JWT exp (default 60) | 60 |
| BOOMI_COMPONENT_GET_DEADLINE_SECONDS | No | Wall-clock deadline for component-XML reads (default 90, clamped 1-240) | 90 |
| BOOMI_RT_SLIDING_REFRESH_TTL_SECONDS | No | Sliding lifetime for refresh tokens (default 2592000, 30 days) | 2592000 |
| BOOMI_TOKEN_CACHE_STALE_IF_ERROR_SECONDS | No | Serve last positive token past expiry on Google outage (default 0, off) | 0 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/RenEra-ai/boomi-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server