Shothik MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| celestia_statusC | Check Celestia consensus validator and DA bridge node sync status |
| monad_metricsC | Monitor Monad high-throughput EVM validator execution metrics and JSON-RPC latency |
| oraichain_oracle_healthC | Query Oraichain AI oracle signing health and CosmWasm contract execution status |
| verify_bkash_trxC | Verify a 10-character bKash Mobile Financial Services transaction ID and check settlement status |
| book_steadfast_parcelC | Automate parcel booking with Steadfast courier across Bangladesh with instant tracking code |
| generate_mushak_6_3C | Generate statutory Bangladesh National Board of Revenue (NBR) Mushak-6.3 VAT tax invoice challan |
| execute_sandbox_codeA | Safely execute JavaScript or Python code in an isolated, sandboxed runtime with output capture |
| semantic_memorizeC | Store a semantic user fact, preference, or architectural decision into memory |
| semantic_recallB | Recall relevant context facts and decisions using keyword matching |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Most tools are highly distinct (e.g., generate_mushak_6_3 vs. execute_sandbox_code), but the three blockchain status tools (celestia_status, monad_metrics, oraichain_oracle_health) share a similar monitoring purpose and could cause confusion despite their chain-specific descriptions. No other significant overlaps exist.
Naming conventions are wildly inconsistent: snake_case throughout, but verbs range from `generate_` and `execute_` to `semantic_memorize` (adjective-verb) and `celestia_status` (noun-noun). The mix of action-oriented and noun-phrase names, plus the embedded number in `generate_mushak_6_3`, breaks any predictable pattern.
At 9 tools, the count is not inherently problematic, but the scope is a patched-together set of unrelated domains (VAT, code execution, memory, three blockchains, payments, courier). The count feels arbitrary rather than deliberately scoped, making the tool count reasonable but not well-justified.
There is no coherent domain, so completeness is impossible to satisfy. For memory, only store and recall exist; for blockchains, only status checks for three chains; for Bangladesh services, only VAT, bKash, and one courier. The surface is a shallow grab-bag with obvious gaps in any individual area, likely causing agent failures when more than the basic operation is needed.