Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

TinyFish Guided Research

PYPI · TINYFISH-GUIDED-RESEARCH-MCP · SCANNED SEP 20

Auditable deep-research MCP server powered by TinyFish Search and Fetch.

52 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security50
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 1 of 34 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability75
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1262 tokens (~63/item across 20 items; 20 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "dispatch_parallel_subagents" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 21 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

Install

How do I install the TinyFish Guided Research MCP server?

TinyFish Guided Research runs locally as a PyPI package, launched with uvx tinyfish-guided-research-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · tinyfish-guided-research-mcp

# add to Claude Code
claude mcp add mohdsaleh-tinyfish-guided-research -- uvx tinyfish-guided-research-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "mohdsaleh-tinyfish-guided-research": {
      "command": "uvx",
      "args": [
        "tinyfish-guided-research-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "mohdsaleh-tinyfish-guided-research": {
      "command": "uvx",
      "args": [
        "tinyfish-guided-research-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add mohdsaleh-tinyfish-guided-research -- uvx tinyfish-guided-research-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mohdsaleh-tinyfish-guided-research": {
      "type": "local",
      "command": [
        "uvx",
        "tinyfish-guided-research-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add mohdsaleh-tinyfish-guided-research --command uvx --arg tinyfish-guided-research-mcp
# ~/.hermes/config.yaml
mcp_servers:
  mohdsaleh-tinyfish-guided-research:
    command: "uvx"
    args: ["tinyfish-guided-research-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "mohdsaleh-tinyfish-guided-research": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "tinyfish-guided-research-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add mohdsaleh-tinyfish-guided-research -t stdio -c uvx -a tinyfish-guided-research-mcp
// mcp.json
{
  "mcpServers": {
    "mohdsaleh-tinyfish-guided-research": {
      "command": "uvx",
      "args": [
        "tinyfish-guided-research-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 15 Sept 26 52

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed pypi/tinyfish-guided-research-mcp@1.0.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 34 packages
Packages resolved 34
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 20 exposed · ~1,034 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
assess_claims ~29

Compute deterministic claim resolution and return a complete next-step packet.

NameTypeReqDescription
research_idstringyes
NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

bind_evidence ~82

Bind direct source quotations to existing claims and verify quote presence. This tool does NOT accept semantic stance. Keeping quote binding separate from entailment judgment gives weak client models one bounded operation at a time and prevents a topical passage from becoming support merely because it was attached to a claim.

NameTypeReqDescription
bindingsarrayyes
research_idstringyes
NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

check_server_config ~25

Check API key, DNS, and live TinyFish Search/Fetch endpoint health.

Input schema present but exposes no named parameters.

NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

discovery_search ~51

Run a compact additional retrieval wave; later waves consume the global follow-up budget.

NameTypeReqDescription
purposestringyes
queriesarrayyes
research_idstringyes
retrieval
NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

dispatch_parallel_subagents ~36

Execute independent retrieval tracks concurrently and return only a compact review shortlist.

NameTypeReqDescription
research_idstringyes
tasks
NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

finalize_research ~34

Finalize into an auditable synthesis manifest; do not generate prose inside the MCP.

NameTypeReqDescription
research_idstringyes
NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

get_research_state ~33

Debug/inspection tool. Returns compact protocol state, not full source text.

NameTypeReqDescription
research_idstringyes
NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

get_source_context ~59

Return a few relevant passages from persisted full source content. Use when the client needs a better direct quote without re-fetching the URL.

NameTypeReqDescription
querystring
research_idstringyes
source_idstringyes
NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

init_research ~73

Start a research session with an explicit latency/coverage profile. FAST is the default and preserves the same hard evidence gates while fetching/reviewing fewer candidates and stopping resolved claims early.

NameTypeReqDescription
contestedboolean
max_rounds
mode
topicstringyes
NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

judge_evidence ~66

Assign bounded semantic relation labels to quote-verified evidence. The server owns evidence IDs and quote integrity. The client does exactly one semantic task here: classify the relationship between the displayed quote and its claim.

NameTypeReqDescription
judgmentsarrayyes
research_idstringyes
NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

override_atomicity ~46

Explicitly override an atomicity warning for a maximally atomic claim.

NameTypeReqDescription
claim_idstringyes
reasonstringyes
research_idstringyes
NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

plan_research ~32

Validate and store the research plan before any retrieval.

NameTypeReqDescription
planyes
research_idstringyes
NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

register_claims ~58

Register new claims only; does not accept evidence. This separation prevents claim creation and evidence judgment from being conflated in one call. Server generates every claim_id.

NameTypeReqDescription
claimsarrayyes
research_idstringyes
NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

research_unknowns ~42

Run targeted retrieval only for claims that still need work, then return one compact review packet.

NameTypeReqDescription
gapsarrayyes
research_idstringyes
NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

review_candidates ~90

Unified claim/source review: relevance + direct quote + semantic relation. Initial broad retrieval still uses screen_sources before claims exist. Once claim IDs exist, this is the preferred path for both initial evidence and targeted gap evidence; bind_evidence/judge_evidence remain low-level compatibility tools rather than the normal happy path.

NameTypeReqDescription
research_idstringyes
reviewsarrayyes
NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

review_claim_tensions ~62

Record cross-claim tensions after the claim graph is stable. Mandatory once for contested sessions. Tensions may describe genuine theoretical disagreement even when both claims accurately represent different positions.

NameTypeReqDescription
research_idstringyes
tensionsarrayyes
NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

revise_claim ~69

Replace an incorrect/overbroad active claim without leaving the parent unresolved. The old claim is superseded automatically. Use this for semantic revision; use split_claim when one claim must become multiple children.

NameTypeReqDescription
claim_idstringyes
replacementyes
research_idstringyes
NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

screen_sources ~36

Initial semantic source gate over only the server-provided review shortlist.

NameTypeReqDescription
research_idstringyes
screeningsarrayyes
NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

split_claim ~44

Split a compound claim. The parent is superseded automatically.

NameTypeReqDescription
childrenarrayyes
parent_claim_idstringyes
research_idstringyes
NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

verify_citations ~67

Server-owned citation integrity + coverage audit. Normal use: pass research_id only. The server automatically selects the strongest quote-verified winning evidence for each strongly resolved claim. Optional citations are accepted only as explicit client overrides.

NameTypeReqDescription
citations
research_idstringyes
NameTypeReqDescription
agent_rulesarray
dataobject
next_action
protocol_versionstring
quality_gate
statusstringyes

No examples provided.

Common questions

What is the TinyFish Guided Research MCP server?

TinyFish Guided Research is an MCP server listed in the public MCP registry as io.github.MohdSaleh/tinyfish-guided-research. Auditable deep-research MCP server powered by TinyFish Search and Fetch. This page covers its PyPI package (tinyfish-guided-research-mcp).

Is the TinyFish Guided Research MCP server safe to use?

TinyFish Guided Research scores 52 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the TinyFish Guided Research MCP server expose?

TinyFish Guided Research exposes 20 tools: check_server_config, init_research, plan_research, dispatch_parallel_subagents, discovery_search, and 15 more. Their descriptions and schemas cost roughly 1,034 tokens of context every time the server is loaded.

Is the TinyFish Guided Research MCP server still maintained?

TinyFish Guided Research is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the TinyFish Guided Research MCP server under?

TinyFish Guided Research declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.